AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Algorithms algorithms	2.6	5.4	2008	17.6 Days	CHF 1800	Submit
Complexities complexities	-	-	2025	15.0 days *	CHF 1000	Submit
Energies energies	3.9	8.3	2008	16.7 Days	CHF 2600	Submit
Entropy entropy	2.1	4.9	1999	20.9 Days	CHF 2600	Submit
Laboratories laboratories	-	-	2024	15.0 days *	CHF 1000	Submit
Machine Learning and Knowledge Extraction make	8.4	12.7	2019	18.7 Days	CHF 1800	Submit
Materials materials	3.7	7.0	2008	14.4 Days	CHF 2600	Submit

13 pages, 946 KB

Open AccessArticle

Model Checking-Based Radiomics for Diagnosis and Prognosis of Oral Cavity Tumors: A Two-Tier Approach

by Maria Paola Belfiore, Maria Rita Cristiano, Valeria Sorgente, Giulia Varriano, Vittoria Nardone, Maria Chiara Brunese, Salvatore Cappabianca, Antonella Santone and Luca Brunese

Mach. Learn. Knowl. Extr. 2026, 8(7), 202; https://doi.org/10.3390/make8070202 - 10 Jul 2026

Viewed by 149

Abstract

Background: Oral cavity tumors are often diagnosed at advanced stages due to non-specific early symptoms and limitations in imaging sensitivity. This study proposes a novel methodology combining Radiomics and Model Checking to improve diagnosis and prognosis. Methods: A retrospective dataset of 18 patients [...] Read more.

Background: Oral cavity tumors are often diagnosed at advanced stages due to non-specific early symptoms and limitations in imaging sensitivity. This study proposes a novel methodology combining Radiomics and Model Checking to improve diagnosis and prognosis. Methods: A retrospective dataset of 18 patients (12 with oral squamous cell carcinoma and 6 healthy controls) who underwent contrast-enhanced MRI was analyzed. Radiomic features were extracted and selected, then encoded into formal models. A two-tier Model Checking approach was applied: (i) classification of healthy vs. pathological patients and (ii) prediction of treatment response. Results: The proposed method achieved a diagnostic accuracy of 93% and a prognostic accuracy of 75%. The approach demonstrated robustness even with a limited dataset, outperforming traditional data-driven methods in small-sample settings. Conclusions: The integration of Radiomics with Model Checking provides an explainable and effective tool for early detection and prognosis of oral cavity tumors. This approach may support clinicians as a decision-making aid, particularly in data-scarce scenarios. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

13 pages, 6882 KB

Open AccessArticle

Sensitivity Analysis of Cracking Behavior in Fully Ceramic Microencapsulated Fuel

by Shichao Liu, Haoyue Huang, Chi Chen, Yanli Zhao, Yuanming Li, Chenxi Li and Yi Zhou

Materials 2026, 19(14), 2938; https://doi.org/10.3390/ma19142938 - 8 Jul 2026

Viewed by 115

Abstract

To identify the key factors influencing the cracking behavior of fully ceramic microencapsulated (FCM) fuel, this study employed the MOOSE V1.3 multiphysics coupling platform and the cohesive phase-field fracture theory to simulate crack initiation and propagation in FCM fuel, with particular attention to [...] Read more.

To identify the key factors influencing the cracking behavior of fully ceramic microencapsulated (FCM) fuel, this study employed the MOOSE V1.3 multiphysics coupling platform and the cohesive phase-field fracture theory to simulate crack initiation and propagation in FCM fuel, with particular attention to the effects of particle spacing and residual pore in the matrix. Results showed that during early irradiation stages, in the absence of matrix defects, particle spacing had minimal influence on the distribution of the maximum principal stress. However, when residual pore was present in the SiC matrix, significant stress concentration occurred at the porosity sites, where the maximum principal stress was localized. Smaller particle spacing promoted crack initiation in the SiC matrix between adjacent particles and led to a higher number of cracks under the same fast neutron fluence. In the presence of residual pore, crack nucleation occurred at porosity sites even at low neutron fluence; at a fluence of 2.3 × 10²⁵ n/m², through-thickness cracks formed in FCM fuel containing residual pore, resulting in the loss of fission product containment capability. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

21 pages, 4944 KB

Open AccessArticle

Simulation Study on the Mechanical Properties of Fuzz Buttons

by Xiuping Dong, Zhongping Zhang and Mingji Huang

Materials 2026, 19(13), 2927; https://doi.org/10.3390/ma19132927 - 7 Jul 2026

Viewed by 135

Abstract

Fuzz buttons are formed by interweaving and compacting fine metallic wires, resulting in a highly porous architecture with complex internal contact interactions. Their compressive behavior is governed by the evolution of wire–wire contacts, frictional sliding, local bending, and plastic deformation, which cannot be [...] Read more.

Fuzz buttons are formed by interweaving and compacting fine metallic wires, resulting in a highly porous architecture with complex internal contact interactions. Their compressive behavior is governed by the evolution of wire–wire contacts, frictional sliding, local bending, and plastic deformation, which cannot be adequately captured by conventional homogenized models. To address this limitation, a process-informed finite element modeling approach based on virtual fabrication is proposed. First, the spatial trajectories of 24 beryllium copper wires are generated using a parametric three-dimensional weaving algorithm and smoothed by cubic spline interpolation to obtain continuous wire centerlines. The resulting preform is then virtually compacted to reconstruct the densified wire network and its contact topology. The model employs a globally controlled solid-element mesh, a penalty-based general contact algorithm, a Coulomb friction model, and an explicit quasi-static solution scheme. The size-dependent plastic response of the fine wires is further incorporated through a Nix–Gao-based correction to the constitutive relation. The model is validated against quasi-static compression experiments at compressive strains of 15%, 20%, and 25%. The relative errors in the predicted peak forces are 2.12%, 5.65%, and 6.81%, respectively, while the corresponding coefficients of determination for the force–displacement curves are 0.984, 0.970, and 0.973. The model successfully reproduces the nonlinear loading–unloading response and hysteretic energy dissipation over the investigated strain range. The proposed approach provides a physically grounded numerical framework for predicting the compressive behavior of fuzz buttons and investigating the mesoscopic mechanics of complex interwoven wire networks. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

29 pages, 26733 KB

Open AccessArticle

Targeted Adversarial Camouflage Texture for Fooling Object Detectors via Native Supervision Redirection

by Xingyu Di, Wei Cai, Xin Wang, Zhongjie Yin, Shuhui Li and Haoran Jia

Entropy 2026, 28(7), 718; https://doi.org/10.3390/e28070718 - 24 Jun 2026

Viewed by 357

Abstract

Adversarial camouflage has attracted growing research attention owing to its ability to execute multi-view, persistent attacks in real physical environments, outperforming conventional single-view adversarial patches. However, most existing methods are confined to non-targeted attacks, which induce arbitrary incorrect detection results without specifying target [...] Read more.

Adversarial camouflage has attracted growing research attention owing to its ability to execute multi-view, persistent attacks in real physical environments, outperforming conventional single-view adversarial patches. However, most existing methods are confined to non-targeted attacks, which induce arbitrary incorrect detection results without specifying target categories. This ambiguity weakens attack destructiveness and stealthiness, posing limitations for security evaluation of real-world vision systems. To address this gap, we present TACT, an approach built upon the full-coverage physical camouflage pipeline. By replacing the original category supervision with a predefined target class, TACT redirects the optimization gradient to guide 3D texture toward the target category features. Such a scheme only employs the inherent feature alignment mechanism of off-the-shelf object detectors, without redesigning network modules, defining novel loss functions, or modifying the rendering pipeline. Extensive experiments across digital and physical domains validate its effectiveness: on seven mainstream general-purpose object detectors, TACT-person achieves an average targeted attack success rate of 51.91%, and delivers cross-architecture and cross-version transferability. In physical tests, TACT-bird reduces mAP50-95 by 59.87% on YOLOv8, yet a TCER–TASR gap suggests that the physical pipeline acts as a low-pass filter: coarse-grained target classes transfer robustly while fine-grained ones suffer feature collapse. These results confirm the viability of native supervision redirection and reveal an empirical pattern: coarse-grained target classes transfer more robustly through the physical pipeline than fine-grained ones, suggesting that target class feature granularity consistently influences physical-domain attack effectiveness. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

35 pages, 2314 KB

Open AccessArticle

From Legal Text to NP-Complete Decision Models: MPNet Retrieval and Policy Information Extraction

by Aigerim Aitim, Anel Auyezova, Bakhtgerey Sinchev and Aksulu Mukhanova

Mach. Learn. Knowl. Extr. 2026, 8(6), 163; https://doi.org/10.3390/make8060163 - 12 Jun 2026

Viewed by 318

Abstract

This study addresses the growing need to convert unstructured legal and policy documents into formal computational models that support transparent decision-making. The purpose of the work is to develop an applied framework that connects Legal NLP and policy information extraction with canonical combinatorial [...] Read more.

This study addresses the growing need to convert unstructured legal and policy documents into formal computational models that support transparent decision-making. The purpose of the work is to develop an applied framework that connects Legal NLP and policy information extraction with canonical combinatorial decision models, including set cover, set packing, subset sum, vertex cover, and independent set. The proposed method combines MPNet-based dense semantic retrieval for locating relevant legal passages, a Legal NLP layer for extracting obligations, prohibitions, exceptions, thresholds, and eligibility conditions, and a formal modeling stage that maps the extracted constraints to NP-complete formulations, including set cover, set packing, subset sum, vertex cover, and independent set. The framework is designed to transform regulatory text into machine-interpretable structures suitable for constraint-aware reasoning and policy analysis. The results show that the integration of semantic retrieval and structured legal information extraction improves the consistency, interpretability, and practical usability of formal problem construction from legal and policy documents. The proposed approach provides a reproducible bridge between legal text analytics and combinatorial decision modeling and supports legal decision support, compliance analysis, and policy-oriented intelligent systems. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

29 pages, 7644 KB

Open AccessArticle

Information Entropy-Guided Multi-Scale Feature Fusion for Crowd Density Estimation

by Zixun Liu, Tianle Yang and Yongjie Wang

Entropy 2026, 28(6), 617; https://doi.org/10.3390/e28060617 - 30 May 2026

Viewed by 220

Abstract

The spatial heterogeneity of crowd distributions poses significant challenges for density estimation. Dense regions exhibit high local information entropy due to severe occlusion and feature ambiguity, while sparse regions and backgrounds carry progressively lower informational complexity. To address this, we propose an entropy-inspired [...] Read more.

The spatial heterogeneity of crowd distributions poses significant challenges for density estimation. Dense regions exhibit high local information entropy due to severe occlusion and feature ambiguity, while sparse regions and backgrounds carry progressively lower informational complexity. To address this, we propose an entropy-inspired crowd density estimation framework that allocates computational attention in proportion to the local information complexity of crowd regions. A Density-Guided Map (DGMap), constructed from nearest-neighbor distance statistics of head annotations, serves as a proxy for local information entropy, enabling the model to differentiate among dense, sparse, and isolated pedestrian regions. The proposed network, termed DGCC-Net, comprises four components: a Twins-Transformer backbone for hierarchical feature extraction, a Local Attention Module (LAM) that enhances high-resolution features through multi-scale receptive fields and rotational attention, a Multi-Level Feature Fusion Module (MLFM) with cross-scale dense connectivity and learnable branch weights for integrating semantic and spatial information, and a Density Guidance Module (DGM) supervised by the entropy-inspired DGMap to achieve density-adaptive feature refinement. Extensive experiments on four benchmark datasets (ShanghaiTech PartA, UCF-QNRF, UCF_CC_50, and JHU-Crowd++) demonstrate that DGCC-Net achieves competitive or state-of-the-art performance, validating the effectiveness of entropy-inspired attention allocation in heterogeneous crowd scenarios. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

22 pages, 8752 KB

Open AccessArticle

Water and Gas Flooding Oil Monitored by a Real-Time U-Net Neural Network-Based Method

by Jie Zhang, Maolei Cui and Rui Wang

Energies 2026, 19(11), 2601; https://doi.org/10.3390/en19112601 - 28 May 2026

Viewed by 261

Abstract

There are several methods which are utilized for flooding oil process monitoring, such as the seismic methods, and the electromagnetic methods. As the gas flooding oil process is complicated, conventional methods are not capable of monitoring the gas flooding oil process accurately. This [...] Read more.

There are several methods which are utilized for flooding oil process monitoring, such as the seismic methods, and the electromagnetic methods. As the gas flooding oil process is complicated, conventional methods are not capable of monitoring the gas flooding oil process accurately. This study utilizes the Ground Penetrating Radar (GPR) method to monitor the CO₂ flooding oil and water flooding oil processes, as the difference in dielectric constants and conductivity of CO₂, oil and water is utilized to infer distributions of CO₂, oil and water. Moreover, as GPR data processing is time-consuming, it is impossible to process the GPR data in real-time by a conventional method, such as the full waveform inversion method. This study utilizes U-Net neural networks to invert for the subsurface dielectric constants and conductivity distributions of CO₂, oil and water in real-time. A deep learning inversion network based on the U-Net architecture is trained to extract multi-scale features through an encoder–decoder structure, achieving an end-to-end mapping from GPR echo signals to subsurface electrical parameters. The study utilizes the gprMax forward tool to simulate the dynamic response changes in rock-electrical parameters during flooding and constructs a high-resolution training dataset of 100,000 samples. Each sample contains the relationships between a subsurface electrical parameter model and its corresponding multi-transmitter, multi-receiver GPR responses. This method was first tested by the synthetic data of oil–water flooding and oil–water–gas flooding, and then it was tested by observed data from physical core experiments. Numerical and physical core experimental results show that the method accurately inverts the electrical parameter distributions of oil, water, and gas in the sandstone model, successfully capturing the position and morphology changes in the displacement front. The average relative error of dielectric constant inversion is controlled within 8% with the error mainly from the low dielectric constant regions and the relative error of conductivity is smaller than 10%, with the error mainly concentrated in high-conductivity water regions for conductivity inversion results. The results reveal the feasibility and superiority of the neural network-based deep learning method in GPR electromagnetic inversion, providing a new method for real-time flooding monitoring and intelligent reservoir development during oil and gas flooding. Moreover, the proposed approach offers a fast inversion solution and is less affected by the initial model and noise. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

29 pages, 879 KB

Open AccessArticle

A Unified Methodology for Direct and Inverse Problems in Steady-State Thermal–Hydraulic Networks

by Mirco Ganz, Frank Tillenkamp and Christian Ghiaus

Energies 2026, 19(11), 2587; https://doi.org/10.3390/en19112587 - 27 May 2026

Viewed by 359

Abstract

Steady-state thermal–hydraulic network models are widely used for the analysis, design, and operation of energy systems. While direct problems with prescribed boundary conditions can often be solved efficiently, inverse problems such as set-point tracking and parameter identification are commonly addressed through repeated solution [...] Read more.

Steady-state thermal–hydraulic network models are widely used for the analysis, design, and operation of energy systems. While direct problems with prescribed boundary conditions can often be solved efficiently, inverse problems such as set-point tracking and parameter identification are commonly addressed through repeated solution of the corresponding direct problem. For large-scale networks with strong nonlinear couplings, such nested strategies can become computationally expensive and numerically burdensome. This paper presents a unified methodology for the solution of direct and inverse steady-state thermal–hydraulic problems within a single modeling workflow. In contrast to classical nested approaches, inverse problems are formulated in a simultaneous analysis and design framework, in which system states and selected system inputs are treated as unknowns simultaneously. The methodology combines externally causal component representations with acausal network balance relations in order to expose the structural dependencies of the assembled system and enable graph-based tearing reduction. Component-local evaluations, including possible component-internal nonlinear calculations, are encapsulated within the component models, while the nonlinear network closure problem is restricted to a reduced set of tearing variables.. Direct problems are solved by nonlinear root finding on the tearing-reduced residual system, whereas inverse problems are posed as tearing-reduced residual-constrained nonlinear programs with equality, inequality, and bound constraints. The methodology is demonstrated on a vapor-compression refrigeration cycle, where compressor speed and expansion valve opening are adjusted to satisfy prescribed cooling-load and superheat targets under varying condenser inlet temperatures. Implemented in Python, the proposed methodology supports transparent and reproducible modeling and provides a practical basis for simulation, set-point tracking, and constrained optimization of coupled thermal–hydraulic networks. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

31 pages, 6041 KB

Open AccessArticle

Integrated Two-Stage Scheduling Framework for Compressor Units via a Hybrid Algorithm and Dynamic Programming

by Cheng Chen, Chun Zhao, Yunpeng Zhang, Xi Gao, Linying Chen, Qi Wei, Likai Xing, Feng Song and Xiaoming Chen

Energies 2026, 19(11), 2566; https://doi.org/10.3390/en19112566 - 26 May 2026

Viewed by 330

Abstract

Electrically driven compressors are a primary energy consumer in natural gas storage facilities. Formulating an optimal gas injection allocation strategy considering their nonlinear characteristics and time-of-use (TOU) electricity prices is crucial. However, single-model optimizations struggle with this due to high dimensionality and strongly [...] Read more.

Electrically driven compressors are a primary energy consumer in natural gas storage facilities. Formulating an optimal gas injection allocation strategy considering their nonlinear characteristics and time-of-use (TOU) electricity prices is crucial. However, single-model optimizations struggle with this due to high dimensionality and strongly coupled variables. To overcome these challenges, we propose a two-stage “instantaneous load allocation—day-ahead scheduling” framework. Stage I employs a hybrid algorithm (ICSA-WOA) to optimize load allocations across various flow rates, generating a lookup table that effectively decouples the underlying physical model. Stage II utilizes this table alongside TOU prices to perform rapid day-ahead scheduling via dynamic programming (DP). Results demonstrate that ICSA-WOA achieves superior comprehensive performance compared to seven classical swarm intelligence algorithms. Furthermore, joint optimization of the pressure ratio and load via ICSA-WOA reduces the total power consumption by 9.7–10.9% relative to traditional fixed-ratio modes. Most significantly, while rigorously ensuring daily injection targets and safety, the proposed method reduces daily electricity costs by 3.3–14.2% compared to single-model approaches, providing a reasonable strategy for economic gas storage operations. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

46 pages, 4652 KB

Open AccessArticle

Research on Error Compensation Methods of Dynamic Gravity Measurement Based on Swarm Cooperation Evolution Strategy and Optimized LSTM

by Xinyu Li, Zhaofa Zhou, Zhili Zhang, Zhe Liang, Zhenjun Chang and Yiyi Li

Entropy 2026, 28(5), 568; https://doi.org/10.3390/e28050568 - 19 May 2026

Viewed by 235

Abstract

Dynamic gravity measurement, crucial for engineering application, suffers accuracy degradation due to errors induced by carrier maneuvers. To address the limitations of conventional swarm optimization algorithms in precision, stability, and generalizability, this study proposes a Swarm Cooperation Evolution Strategy (SCES) that efficiently integrates [...] Read more.

Dynamic gravity measurement, crucial for engineering application, suffers accuracy degradation due to errors induced by carrier maneuvers. To address the limitations of conventional swarm optimization algorithms in precision, stability, and generalizability, this study proposes a Swarm Cooperation Evolution Strategy (SCES) that efficiently integrates multiple algorithms. The proposed SCES is extensively evaluated on the CEC2022 benchmark suite in comparison with several cooperative fusion-related algorithms and representative single optimization algorithms. The experimental results demonstrate that SCES achieves an overall effectiveness score of 0.034 and an optimal accessibility rate exceeding 95%. Compared to the best-performing fusion-based algorithm, these metrics represent improvements of 54.67% and 31.11%, respectively. Moreover, relative to the best-performing single optimization algorithm, the improvements amount to 37.73% and 32.69%, respectively. These findings robustly validate the superior performance of the proposed algorithm. Moreover, an in-depth investigation based on SCES into dynamic error compensation methodologies is conducted. Firstly, a polynomial compensation model is established through error mechanism analysis, with parameters identified via SCES. Secondly, a data-driven compensation model employing a multi-layer long short-term memory (LSTM) network optimized via neural architecture search (NAS) guided by SCES is proposed, circumventing the performance limitations inherent in manually designed networks. Furthermore, an innovative two-stage hybrid strategy is introduced. Systematic trend errors are compensated using the polynomial model, followed by the NAS-LSTM model addressing complex residual nonlinear errors, effectively combining mechanism-based and data-driven approaches. Validation on three lines exhibiting varying maneuverability shows all methods significantly improve accuracy. The hybrid strategy delivers optimal performance, achieving 0.58 mGal internal coincidence accuracy on stable lines and up to 91.58% improvement in external coincidence accuracy under high maneuverability. This research provides an effective high-precision dynamic gravity measurement and compensation solution, advancing engineering applications. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

29 pages, 1270 KB

Open AccessSystematic Review

Reactive to Predictive Mobility Management: A Systematic Review of ML-Driven Handover Optimization in 5G and Beyond

by Teresia Ankome and Eisuke Hanada

Mach. Learn. Knowl. Extr. 2026, 8(5), 133; https://doi.org/10.3390/make8050133 - 18 May 2026

Viewed by 647

Abstract

Handover optimization is essential for seamless connectivity in 5G and beyond networks. Existing approaches present fundamental challenges of centralized solutions achieving coordination and accuracy but creating privacy risks under the General Data Protection Regulation (GDPR), while distributed privacy-preserving approaches protect user data but [...] Read more.

Handover optimization is essential for seamless connectivity in 5G and beyond networks. Existing approaches present fundamental challenges of centralized solutions achieving coordination and accuracy but creating privacy risks under the General Data Protection Regulation (GDPR), while distributed privacy-preserving approaches protect user data but lack the network-wide visibility necessary for optimal mobility decisions. This systematic review synthesizes 49 peer-reviewed studies published between 2010 and 2025, identified through a PRISMA-compliant search across IEEE Xplore, ScienceDirect, SpringerLink, MDPI, ACM Digital Library, and Google Scholar. Eligible studies addressed cellular handover or mobility management using traditional signal-based, Machine Learning, Federated Learning, Software-Defined Networking strategies, and reported quantitative performance metrics. A structured quality assessment evaluated methodological rigor, dataset validation, benchmarking practices, handover-specific metrics, and scalability. Synthesis evidence shows that existing approaches do not simultaneously satisfy critical requirements for next-generation mobility management of accuracy, privacy, scalability, and real-time network-wide coordination. Machine learning achieves high accuracy (up to 97%) but depends on centralized data; Reinforcement Learning supports real-time adaptation but incurs high computational costs; federated learning preserve privacy but suffers from limited global coordination; and software-defined networking enables centralized control but requires continuous transmission of raw data. Evidence quality is further limited to simulation-based assessments and limited real-world datasets. Overall, the reviews identify a clear evolution from reactive threshold-based methods towards proactive prediction and highlights the need for unified, privacy-preserving and globally coordinated handover frameworks. The findings point toward integrating federated learning with Software-Defined Mobile Networking as promising architectural direction for 6G mobility management. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

25 pages, 6560 KB

Open AccessArticle

R-SATNet: Robust Self-Attention Transformer Network for Multi-Step Building Load Forecasting in Smart Energy Systems

by Amel Ksibi, Manel Ayadi, Jawaher Alyami and Ghadah Aldehim

Energies 2026, 19(9), 2248; https://doi.org/10.3390/en19092248 - 6 May 2026

Viewed by 421

Abstract

Accurate multi-step building load forecasting is critical for optimizing energy management in smart grids and reducing operational costs. However, existing forecasting methods struggle with complex temporal dependencies, seasonal variations, and robust performance under noisy conditions. This paper proposes R-SATNet (Robust Self-Attention Transformer Network), [...] Read more.

Accurate multi-step building load forecasting is critical for optimizing energy management in smart grids and reducing operational costs. However, existing forecasting methods struggle with complex temporal dependencies, seasonal variations, and robust performance under noisy conditions. This paper proposes R-SATNet (Robust Self-Attention Transformer Network), a novel deep learning architecture that integrates multi-head self-attention mechanisms with robust optimization techniques for enhanced building load prediction. The proposed framework incorporates temporal feature extraction modules, adaptive noise suppression layers, and multi-scale attention blocks to capture both short-term fluctuations and long-term seasonal patterns. Extensive experiments on real-world building load datasets demonstrate that R-SATNet achieves superior forecasting accuracy with 15.7% lower RMSE and 12.3% improved MAPE compared to state-of-the-art methods. The model maintains robust performance under various noise conditions and provides reliable multi-step predictions up to 24 h ahead, making it highly suitable for practical smart energy system deployments. The proposed framework is validated across six diverse building datasets spanning commercial, residential, industrial, campus, mixed-use, and healthcare facilities, confirming its generalizability and practical applicability in heterogeneous smart energy environments. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

34 pages, 36975 KB

Open AccessArticle

Mathematical Model for Hydropower Plant (HPP) Electricity Forecasting with High Time Resolution

by Viktor Alexiev, Boris Marinov, Vasil Shterev, Rad Stanev and Bozhidar Bozhilov

Energies 2026, 19(9), 2217; https://doi.org/10.3390/en19092217 - 3 May 2026

Viewed by 549

Abstract

Forecasting hydropower plant power production is a great challenge in the context of maintaining power system stability, reliability and efficiency, especially in an age with variable renewable energy sources when demand for electricity is steadily rising. Accurate forecasting methods are a crucial enabler [...] Read more.

Forecasting hydropower plant power production is a great challenge in the context of maintaining power system stability, reliability and efficiency, especially in an age with variable renewable energy sources when demand for electricity is steadily rising. Accurate forecasting methods are a crucial enabler for the operational existence of power systems that rely on renewable sources. And while in the pursuit of increased accuracy of predictions, many recent research works rely on artificial intelligence and machine learning techniques, this study proposes and adopts a more conventional approach with standardized mathematical models to address the problem of hydropower production forecasting. The model predicts the runoff–power relationship. It starts with the normalization of different rain phenomena as a part of the statistical characterization of runoff events. The system transforms rain occurrence to runoff events via the USDA SCS CN model and then feature vectors are composed, which are used to generate kernel coefficients via interpolation. Contrary to models based on artificial intelligence, the proposed approach has several practical advantages requiring a minimal set of input parameters, which significantly reduces data preprocessing demands and allows for a straightforward integration into existing systems, thereby lowering the cost and the implementation and deployment time. Furthermore, the simplicity and universality of the model make it so that it can be adapted across a wide range of hydropower plants of varying scales and with diverse hydrological and meteorological conditions. The model’s performance and prediction accuracy are evaluated using empirical data records of time series over a five-year period for the meteorological parameters and production of an existing real-life hydropower plant in Bulgaria. The performance of the newly proposed model is assessed using widely accepted statistical error metrics, namely, Root Mean Square Error (RMSE), Mean Absolute Error (MAE), the Nash–Sutcliffe Efficiency (NSE) coefficient, and the Pearson correlation coefficient (R). These metrics provide a comprehensive assessment of the forecasts’ precision and effectiveness. The results show that the proposed model offers admissible accuracy with low computational effort. Thus, it can be successfully implemented in practice in a number of hydropower plant production forecasting applications. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

36 pages, 3241 KB

Open AccessArticle

Optimizing Risk–Return Tradeoffs in Wind–Storage Bidding: A Soft Actor–Critic Approach

by Tongtao Ma, Zongxing Li, Dunnan Liu, Zetian Zhao, Yuting Li, Wantong Cai and Qun Li

Energies 2026, 19(8), 1861; https://doi.org/10.3390/en19081861 - 10 Apr 2026

Viewed by 510

Abstract

Strategic bidding for wind–battery hybrid systems is increasingly critical as electricity spot markets transition toward market-oriented mechanisms, particularly in Chinese pilot regions. However, dual uncertainties—wind generation variability and volatile locational marginal prices (LMPs)—expose market participants to significant financial tail risk. This study develops [...] Read more.

Strategic bidding for wind–battery hybrid systems is increasingly critical as electricity spot markets transition toward market-oriented mechanisms, particularly in Chinese pilot regions. However, dual uncertainties—wind generation variability and volatile locational marginal prices (LMPs)—expose market participants to significant financial tail risk. This study develops a risk-constrained reinforcement learning framework for optimal bidding of wind–storage hybrid systems. We employ soft actor–critic (SAC) for continuous action control and integrate conditional value-at-risk (CVaR) into reward design to explicitly penalize low-probability, high-loss outcomes. The framework incorporates realistic operational constraints, including linearized battery degradation costs and a market-compatible single-bid abstraction for hourly settlement. Using one-year historical operational data from a 150 MW wind farm (with a 91-day test period), we find that storage integration increases annual profit by 108.4–114.2% relative to wind-only operation. Critically, the SAC–CVaR policy (η = 0.35) preserves 97.3% of risk-neutral profit ($7.71 M vs. $7.93 M) while substantially mitigating downside risk: CVaR@95% improves by 42.4% (−$549 vs. −$952) and VaR@95% improves by 30.1% (−$275 vs. −$393). The trained policy achieves sub-millisecond inference (0.262 ms per decision, ~3820 decisions/s), corresponding to a 3.8 × 10⁴–5.7 × 10⁴× speedup over optimization-based solvers (10–15 s per decision), enabling real-time deployment. Behavioral analysis reveals that the agent learns adaptive, forecast-normalized bidding strategies with more conservative reporting in high-price regimes and counter-cyclical battery dispatch patterns, demonstrating effective coordination between profitability and risk control under volatile market conditions. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

38 pages, 1822 KB

Open AccessReview

UAV-Based Infrared Thermography for Qualitative and Quantitative Building Energy Assessment: A Review

by Seyed Amirhossein Saei Marand, Milad Mahmoodzadeh and Phalguni Mukhopadhyaya

Energies 2026, 19(7), 1776; https://doi.org/10.3390/en19071776 - 4 Apr 2026

Cited by 2 | Viewed by 1412

Abstract

The growing demand for energy-efficient buildings and the urgent need to retrofit aging infrastructure have driven increased interest in advanced diagnostic technologies. Among these, unmanned aerial vehicle (UAV)-based infrared thermography (IRT) has emerged as a promising non-destructive technique for assessing the thermal performance [...] Read more.

The growing demand for energy-efficient buildings and the urgent need to retrofit aging infrastructure have driven increased interest in advanced diagnostic technologies. Among these, unmanned aerial vehicle (UAV)-based infrared thermography (IRT) has emerged as a promising non-destructive technique for assessing the thermal performance of building envelopes. This review examines recent developments and applications of dynamic infrared thermography (IRT) in the building sector for both qualitative and quantitative thermal assessment, based on previously conducted studies. It highlights the increasing adoption of integrated UAV-based IRT for building inspection and diagnostics, and critically reviews the operational, technical, and methodological advancements in dynamic thermography achieved over the past decade. Furthermore, the review presents a comprehensive framework for operational planning, encompassing environmental conditions, infrared camera configuration, and optimal UAV flight parameters. The key findings identify major challenges associated with dynamic IRT applications, particularly those related to measurement accuracy that currently limit its use for quantitative assessments and synthesize proposed methodologies to address these limitations. The review also highlights the absence of standardized procedures for determining emissivity and reflected apparent temperature in dynamic measurement setups and discusses potential approaches to overcome these gaps. Finally, it outlines priority directions for future research to support the reliable and consistent application of dynamic IRT in quantitative analysis and provides a reference for energy auditors and thermography practitioners to inform the selection of appropriate procedures for accurately quantifying heat loss in building envelopes. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

17 pages, 2939 KB

Open AccessArticle

Optimal Scheduling of Energy Storage Systems in Industrial Microgrids Under Representative Weather Scenarios

by Yu Yang, Sung-Hyun Choi, Kyung-Min Lee and Yong-Sung Choi

Energies 2026, 19(6), 1458; https://doi.org/10.3390/en19061458 - 13 Mar 2026

Viewed by 676

Abstract

To address the operational challenges of industrial microgrids under different weather conditions, this study proposes an optimal dispatch strategy for energy storage systems under representative weather scenarios. Photovoltaic (PV) power generation is first forecast using a Light Gradient Boosting Machine (LightGBM) model, while [...] Read more.

To address the operational challenges of industrial microgrids under different weather conditions, this study proposes an optimal dispatch strategy for energy storage systems under representative weather scenarios. Photovoltaic (PV) power generation is first forecast using a Light Gradient Boosting Machine (LightGBM) model, while the load input is prepared based on recent historical demand patterns, and the forecasting performance is evaluated under representative sunny and cloudy scenarios. A mathematical microgrid model incorporating PV generation, battery energy storage, load demand, and grid interaction is then established, in which the total operating cost is minimized subject to time-of-use electricity pricing, battery degradation, and state-of-charge (SOC) constraints. Based on this formulation, an optimization-based day-ahead scheduling strategy is implemented. Under the selected representative sunny and cloudy conditions, the proposed method reduced the daily operating cost by 19.93% and 4.44%, respectively. Over seven representative days, the average cost reduction rate reached 12.54%, thereby confirming its economic effectiveness under representative weather scenarios. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

41 pages, 2517 KB

Open AccessReview

A Comparative Review of Modeling and Metaheuristic Parameter Identification Strategies for Zero-Dimensional PEMFC Polarization Models

by Yesheng Fang, Fuyong Yang, Yanfeng Xing, Xiaobing Zhang, Wei Wang and Shengyao Lin

Energies 2026, 19(6), 1438; https://doi.org/10.3390/en19061438 - 12 Mar 2026

Viewed by 569

Abstract

Proton exchange membrane fuel cells (PEMFCs) are promising energy conversion de-vices owing to high efficiency and zero local emissions. Accurate PEMFC performance assessment and control require well-posed models, whose predictive accuracy is largely determined by the correct calibration of key parameters. Metaheuristic algorithms [...] Read more.

Proton exchange membrane fuel cells (PEMFCs) are promising energy conversion de-vices owing to high efficiency and zero local emissions. Accurate PEMFC performance assessment and control require well-posed models, whose predictive accuracy is largely determined by the correct calibration of key parameters. Metaheuristic algorithms (MHAs) have therefore been widely applied to PEMFC stack parameter estimation, but their rapid proliferation calls for a more systematic and fine-grained synthesis. This review refines the taxonomy of PEMFC mathematical modeling approaches and summarizes Zero-Dimensional PEMFC modeling methods, key parameters, and representative improvement directions aimed at reducing identification difficulty while retaining physical meaning. Newly developed MHAs and enhanced variants of existing methods are then surveyed, and over 40 distinctive optimization approaches are selected for systematic comparison. Modeling approaches and parameter identification methodologies are summarized. In addition, an algorithm selection guide and 26 representative algorithms with their variants are compiled and benchmarked across the five most widely used commercial PEMFC models to enable cross-model comparison. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

31 pages, 2797 KB

Open AccessArticle

Safe Soft Actor–Critic for Online Transmission Interface Power Flow Control

by Ji Zhang, Liudong Zhang, Qi Li, Di Shi and Yi Wang

Energies 2026, 19(5), 1358; https://doi.org/10.3390/en19051358 - 7 Mar 2026

Viewed by 544

Abstract

The rapid development of a new-type power system dominated by renewable energy has introduced growing complexity and variability into grid topology and dynamics, posing significant challenges for transmission interface power flow control. Traditional regulation methods based on operator experience and deterministic optimization often [...] Read more.

The rapid development of a new-type power system dominated by renewable energy has introduced growing complexity and variability into grid topology and dynamics, posing significant challenges for transmission interface power flow control. Traditional regulation methods based on operator experience and deterministic optimization often fail to achieve real-time optimality under such dynamic conditions. Leveraging its strong capability for autonomous learning and feature perception, deep reinforcement learning (DRL) offers a promising approach for addressing these challenges. This paper proposes a safe DRL-based control framework for online transmission interface power flow regulation. A Safe Soft Actor–Critic (SSAC) agent is developed, embedding power system security constraints directly into the decision process to ensure operational safety. A secure EMS-interactive training platform with containerized parallel learning is established to accelerate model convergence and improve adaptability to changing operating conditions. The developed SSAC agent is deployed in the Jiangsu Power Grid Energy Management System (EMS) for validation. Simulation and field test results demonstrate that the proposed method can generate control strategies online within milliseconds, achieving a 99.3% interface overload mitigation rate and 3.32% network loss reduction, outperforming conventional sensitivity-based optimization methods in both timeliness and economic efficiency. These results demonstrate strong real-time computational capability and compatibility with EMS-based dispatch workflows, indicating promising practical deployment potential for transmission interface control in renewable-dominated power systems. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

23 pages, 3612 KB

Open AccessArticle

A Security Framework for Resilient Smart Grids Based on Self-Organizing Graph Neural Cellular Automata

by Rongxu Hou, Yiying Zhang, Siwei Li, Yeshen He and Pizhen Zhang

Algorithms 2026, 19(3), 195; https://doi.org/10.3390/a19030195 - 5 Mar 2026

Viewed by 912

Abstract

As smart grids evolve into complex cyber-physical systems, conventional static defenses struggle to address time-varying topologies and Advanced Persistent Threats (APTs). We propose the Security Framework for Resilient Smart Grids based on Self-Organizing Graph Neural Cellular Automata (SG-GNC). Specifically, a Neural Homeostatic Embedding [...] Read more.

As smart grids evolve into complex cyber-physical systems, conventional static defenses struggle to address time-varying topologies and Advanced Persistent Threats (APTs). We propose the Security Framework for Resilient Smart Grids based on Self-Organizing Graph Neural Cellular Automata (SG-GNC). Specifically, a Neural Homeostatic Embedding (NHE) mechanism utilizes variational graph autoencoders to construct a continuous health manifold for unsupervised anomaly detection, while a Neural Cellular Automata (NCA) engine employs shared-weight local rules to empower nodes with decentralized self-healing capabilities. Finally, a Generative Adversarial Immunity (GAI) strategy facilitates active defense co-evolution, enhancing robustness against zero-day attacks. Experimental results on the IEEE 118 and 300-bus systems demonstrate an average detection accuracy of 98.23%, significantly outperforming benchmarks. In scenarios involving dynamic topology and zero-day attacks, the framework maintains over 96% accuracy with an inference latency of only 9.45 ms. These findings validate the capability of SG-GNC to provide resilient, endogenous defense in complex heterogeneous environments. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

27 pages, 3616 KB

Open AccessArticle

Hybrid Metaheuristic-Based Probabilistic Planning of Weak Power Grids with Renewable Generation and Hydrogen Energy Storage

by Ayman Hussein Badawi, Mohamed M. Zakaria Moustafa, Mostafa S. Hamad, Ayman Samy Abdel-Khalik and Ragi A. R. Hamdy

Energies 2026, 19(5), 1288; https://doi.org/10.3390/en19051288 - 4 Mar 2026

Cited by 2 | Viewed by 582

Abstract

The large-scale integration of wind turbine generators (WTGs) and photovoltaic (PV) generation increases operational uncertainty and can exacerbate stability limitations in weak transmission networks, motivating the use of green hydrogen energy storage systems (HESS). This paper presents a probabilistic planning framework for the [...] Read more.

The large-scale integration of wind turbine generators (WTGs) and photovoltaic (PV) generation increases operational uncertainty and can exacerbate stability limitations in weak transmission networks, motivating the use of green hydrogen energy storage systems (HESS). This paper presents a probabilistic planning framework for the joint siting and sizing of HESS to support hybrid WTG–PV integration under stochastic wind, solar irradiance, and load conditions. The proposed framework explicitly couples Monte Carlo-based probabilistic power flow with weak-grid security constraints by enforcing FVSI-based voltage-stability limits and an SSI-based system-strength requirement within the optimization loop, rather than treating these indices as post-analysis checks. The planning problem is formulated using a weighted-sum scalarization to minimize life-cycle carbon footprint and active power losses, subject to security constraints based on the Fast Voltage Stability Index (FVSI) and a system-strength constraint expressed through a System Strength Index (SSI). To solve the resulting constrained, nonlinear optimization problem, a sequential hybrid metaheuristic that couples Whale Optimization (exploration) with Osprey Optimization (exploitation) is developed. The framework is implemented in MATLAB using MATPOWER and evaluated on a modified IEEE 39-bus system. Simulation results report an annual carbon footprint of 22.16 Mt CO₂eq/yr, an improvement of 9.2% and 5.3% relative to PSO and GA/PSO baselines, respectively, while increasing the weakest-bus SSI to 4.68 (bus 7). The resulting HESS design comprises a 296.9 MW electrolyzer, a 262.7 MW fuel cell, and 28,012 kg of hydrogen storage. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

21 pages, 4694 KB

Open AccessArticle

Fourier-Feature Neural Surrogate for Hemodynamic Field Reconstruction in Stenotic and Bifurcating Flows

by Polydoros N. Papadopoulos and Vasilis N. Burganos

Mach. Learn. Knowl. Extr. 2026, 8(3), 59; https://doi.org/10.3390/make8030059 - 3 Mar 2026

Viewed by 901

Abstract

This work presents a fast neural surrogate capable of reconstructing fully three-dimensional hemodynamic velocity fields in stenotic and bifurcating microvascular geometries with satisfactory accuracy, avoiding repeated, computationally demanding computational fluid dynamics (CFD) simulations. A Fourier-augmented, coordinate-neural surrogate is presented and assessed for rapid [...] Read more.

This work presents a fast neural surrogate capable of reconstructing fully three-dimensional hemodynamic velocity fields in stenotic and bifurcating microvascular geometries with satisfactory accuracy, avoiding repeated, computationally demanding computational fluid dynamics (CFD) simulations. A Fourier-augmented, coordinate-neural surrogate is presented and assessed for rapid computation of three-dimensional blood-flow fields in a sample geometry. The model is trained on detailed CFD data across a parameter set of stenosis severities that feed a direct mapping from spatial coordinates to velocity components. To mitigate spectral bias and improve accuracy in regions of steep gradients, the input space is embedded with random Fourier features and compared against a conventional multilayer perceptron (MLP) backbone. Predictive ability is assessed upon strict hold-out testing, during which certain arteriolar stenosis cases are excluded from training and treated with the Fourier surrogate. Direct comparison with CFD results reveals that the Fourier MLP achieves nearly CFD fidelity with the coefficient of determination R² ≥ 0.994 and offers more than 80% reduction in the normalized errors as provided by conventional MLP, with the precise improvement depending on the severity of stenosis. Centerline velocity and cross-sectional profiles further show that the Fourier MLP reconstructs stenosis speed-up and radial profiles more reliably compared to conventional MLP. These results indicate that Fourier feature embedding provides a simple and effective route to robust full-field hemodynamic surrogates for efficient screening of stenosis configurations without resorting to repeated, heavily demanding CFD simulations. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

27 pages, 8186 KB

Open AccessArticle

Deceptive Waypoint Sequencing Based UAV–UAV Interception Control Using DBSCAN Learning Strategy

by Abdulrazaq Nafiu Abubakar, Ali Nasir and Abdul-Wahid A. Saif

Mach. Learn. Knowl. Extr. 2026, 8(3), 54; https://doi.org/10.3390/make8030054 - 25 Feb 2026

Cited by 1 | Viewed by 1096

Abstract

Modern multi-Unmanned Aerial Vehicle (UAV) attacks pose significant challenges to existing counter-UAV frameworks due to their agility, irregular spatial formations, and increasing reliance on intelligent evasive behaviors. This paper proposes a unified interception architecture that integrates Density-Based Spatial Clustering of Applications with Noise [...] Read more.

Modern multi-Unmanned Aerial Vehicle (UAV) attacks pose significant challenges to existing counter-UAV frameworks due to their agility, irregular spatial formations, and increasing reliance on intelligent evasive behaviors. This paper proposes a unified interception architecture that integrates Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for multi-target grouping, a deceptive waypoint sequencing (DWS) mechanism for adversarial evasion, and a robust sliding-mode backstepping controller augmented with extended state observers (ESOs) for precise tracking under disturbances. DBSCAN enables real-time clustering of attacking UAVs without prior knowledge of the number of formations, producing dynamic centroids that serve as tactical interception references. To counter risky attackers capable of predicting defender trajectories, a novel DWS strategy introduces centroid-relative waypoints that preserve mission objectives while reducing trajectory predictability. Lyapunov-based analysis is developed for stability, guaranteeing uniform ultimate boundedness of the tracking errors. The proposed approach achieves successful interception in both scenarios, with an interception time of 7 s and final interception error of

0.023

m in the single-UAV case, and an interception time of 8 s with final interception error of

0.050

m in the multiple-UAV case, whereas the PID baseline fails to achieve interception under the same conditions. Extensive simulations involving single and multi-cluster engagements demonstrate that the proposed strategy achieves fast, accurate, and deception-resilient interception, outperforming the conventional PID approach in the presence of disturbances, nonlinearities, and dynamic swarm configurations. The obtained results show the effectiveness of integrating adaptive clustering, deceptive planning, and robust nonlinear control for modern UAV–UAV defensive operations. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

20 pages, 4508 KB

Open AccessArticle

Research on Hybrid Deep Learning Modelling for Short-Term Electricity Load Forecasting

by Jihao Huang, Shujun Wang, Shirong Chen, Peng Ye, Haibo Xu, Ziran Wu, Jiahao Chen and Guichu Wu

Energies 2026, 19(4), 1019; https://doi.org/10.3390/en19041019 - 14 Feb 2026

Viewed by 666

Abstract

Electricity load forecasting is of high importance for electricity management. Modern power systems are complex and diverse, resulting in increased randomness and nonlinear factors of electricity load data, which greatly increases the difficulty of forecasting. This paper proposes a hybrid-deep-learning-based load forecasting method, [...] Read more.

Electricity load forecasting is of high importance for electricity management. Modern power systems are complex and diverse, resulting in increased randomness and nonlinear factors of electricity load data, which greatly increases the difficulty of forecasting. This paper proposes a hybrid-deep-learning-based load forecasting method, named DCFformer (DFT-CNN-FEDformer), for short-term load forecasting (STLF) tasks. The method first employs the discrete Fourier transform (DFT) to denoise time-sequence data on electricity load, so that fluctuations caused by incidents can be reduced. Secondly, it utilizes a convolutional neural network (CNN) that produces sequences of local features extracted from the denoised time sequences. Thirdly, a FEDformer network is applied to perform load forecasting by using extracted feature sequences. In the experiments, we utilize datasets from three regional power systems or apparatuses to compare the proposed DCFformer with other approaches, and the results show that, under the same conditions, DCFformer outperforms the competitors in forecasting precision, which proves the significance of its performance and practicality. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

21 pages, 1511 KB

Open AccessArticle

SKNet-GAT: A Novel Multi-Source Data Fusion Approach for Distribution Network State Estimation

by Huijia Liu, Chengkai Yin and Sheng Ye

Energies 2026, 19(4), 1012; https://doi.org/10.3390/en19041012 - 14 Feb 2026

Cited by 1 | Viewed by 503

Abstract

This paper tackles the growing uncertainty in distribution networks caused by distributed generation, load fluctuations, and frequent topological changes. It proposes a multi-source data fusion framework using enhanced selective convolution (SKNet) and graph attention networks (GAT). First, heterogeneous measurement data, including Phasor Measurement [...] Read more.

This paper tackles the growing uncertainty in distribution networks caused by distributed generation, load fluctuations, and frequent topological changes. It proposes a multi-source data fusion framework using enhanced selective convolution (SKNet) and graph attention networks (GAT). First, heterogeneous measurement data, including Phasor Measurement Unit (PMU) and Supervisory Control and Data Acquisition (SCADA) data, are processed through a unified normalization and outlier elimination technique to ensure data quality. Second, SKNet is utilized to extract spatiotemporal multi-scale features, improving the detection of both rapid disturbances and long-term trends. Third, the extracted features are fed into GAT to model node electrical couplings, while power flow residual constraints are embedded in the loss function to enforce the physical validity of the estimated states. This physics-informed design overcomes a key limitation of pure data-driven models and enables an end-to-end framework that integrates data-driven learning with physical mechanism constraints. Finally, comprehensive validation is performed on the improved IEEE 33-node and IEEE 123-node test systems. The test scenarios include Gaussian measurement noise, data outliers, missing measurements, and topological changes. The results show that the proposed method outperforms baseline models such as Multi-Scale Graph Attention Network (MS-GAT), Bidirectional Long Short-Term Memory (BiLSTM), and traditional weighted least squares (WLS). It achieves Root Mean Square Error (RMSE) reductions of up to 18% and Mean Absolute Error (MAE) reductions of up to 15%. The average inference latency is only 10–18 ms. Even under unknown topological changes, the estimation error increases by only 15–25%. These results demonstrate the superior accuracy, robustness, and real-time performance of the proposed method for intelligent distribution network state estimation. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

46 pages, 6120 KB

Open AccessReview

Integrating Large Language Models into Traffic Systems: Integration Levels, Capability Boundaries, and an Information-Theoretic Perspective

by Wenwen Tu, Junfan Li, Feng Xiao, Xiaosa Wang and Yong Lu

Entropy 2026, 28(2), 211; https://doi.org/10.3390/e28020211 - 11 Feb 2026

Cited by 1 | Viewed by 1827

Abstract

Large language models (LLMs) are fundamentally transforming intelligent traffic systems by enabling semantic abstraction, probabilistic reasoning, and multimodal information fusion across heterogeneous data. This review examines existing research on LLM integration, ranging from data representation to autonomous agents, through an information-theoretic lens, conceptualizing [...] Read more.

Large language models (LLMs) are fundamentally transforming intelligent traffic systems by enabling semantic abstraction, probabilistic reasoning, and multimodal information fusion across heterogeneous data. This review examines existing research on LLM integration, ranging from data representation to autonomous agents, through an information-theoretic lens, conceptualizing LLMs as entropy-minimizing probabilistic systems that shape their capabilities in uncertainty modeling and semantic compression. We identify core integration patterns and analyze fundamental limitations arising from the inherent mismatch between discrete, entropy-driven LLM reasoning and the continuous, causal, and safety-critical nature of physical traffic environments. This reflects a deep structural tension rather than mere technical gaps. We delineate clear boundaries: LLMs are indispensable for managing high semantic entropy in tasks like contextual understanding and knowledge integration, whereas classical physics-based and optimization models remain essential in domains requiring ultra-low physical, temporal, and causal/normative entropy, such as real-time control and safety verification. Finally, we propose a forward-looking research agenda centered on hybrid intelligence architectures that bridge semantic information processing with physical system modeling for next-generation traffic systems. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

2 pages, 169 KB

Open AccessCorrection

Correction: Cherif Bilio et al. Multi-Objective Optimization of Off-Grid Hybrid Renewable Energy Systems for Sustainable Agricultural Development in Sub-Saharan Africa. Energies 2025, 18, 5058

by Tom Cherif Bilio, Mahamat Adoum Abdoulaye and Sebastian Waita

Energies 2026, 19(4), 891; https://doi.org/10.3390/en19040891 - 9 Feb 2026

Viewed by 324

Abstract

There was a typographical error in the original publication [...] Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

20 pages, 1202 KB

Open AccessPerspective

The Innovative Potential of Artificial Intelligence Applied to Patient Registries to Implement Clinical Guidelines

by Sebastiano Gangemi, Alessandro Allegra, Mario Di Gioacchino, Luca Gammeri, Irene Cacciola and Giorgio Walter Canonica

Mach. Learn. Knowl. Extr. 2026, 8(2), 38; https://doi.org/10.3390/make8020038 - 7 Feb 2026

Cited by 1 | Viewed by 1946

Abstract

Guidelines provide specific recommendations based on the best available medical knowledge, summarizing and balancing the advantages and disadvantages of various diagnostic and treatment options. Currently, consensus methods are the best and most common practices in creating clinical guidelines, even though these approaches have [...] Read more.

Guidelines provide specific recommendations based on the best available medical knowledge, summarizing and balancing the advantages and disadvantages of various diagnostic and treatment options. Currently, consensus methods are the best and most common practices in creating clinical guidelines, even though these approaches have several limitations. However, the rapid pace of biomedical innovation and the growing availability of real-world data (RWD) from clinical registries (containing data like clinical outcomes, treatment variables, imaging, and laboratory results) call for a complementary paradigm in which recommendations are continuously stress-tested against high-quality, interoperable data and auditable artificial intelligence (AI) pipelines. AI, based on information retrieved from patient registries, can optimize the process of creating guidelines. In fact, AI can analyze large volumes of data, ensuring essential tasks such as correct feature identification, prediction, classification, and pattern recognition of all information. In this work, we propose a four-phase lifecycle, comprising data curation, causal analysis and estimation, objective validation, and real-time updates, complemented by governance and machine learning operations (MLOps). A comparative analysis with consensus-only methods, a pilot protocol, and a compliance checklist are provided. We believe that the use of AI will be a valuable support in drafting clinical guidelines to complement expert consensus and ensure continuous updates to standards, providing a higher level of evidence. The integration of AI with high-quality patient registries has the potential to substantially modernize guideline development, enabling continuously updated, data-driven recommendations. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

24 pages, 2052 KB

Open AccessArticle

The Impact of Electric Vehicle Hosting Factors on Distribution Network Performance Using an Impedance-Based Heuristic Approach

by Abdullah Alrashidi, Nora Elayaat, Adel A. Abou El-Ela, Ashraf Fahmy, Ismail Hafez, Tamer Attia and Abdelazim Salem

Energies 2026, 19(3), 753; https://doi.org/10.3390/en19030753 - 30 Jan 2026

Cited by 1 | Viewed by 609

Abstract

The fast adoption of electric vehicles (EVs) and the integration of renewable distributed generators (DGs) provide significant operational issues for radial distribution networks (RDNs), notably in terms of power losses, voltage variations, and system stability. This paper investigates the optimal placement and sizing [...] Read more.

The fast adoption of electric vehicles (EVs) and the integration of renewable distributed generators (DGs) provide significant operational issues for radial distribution networks (RDNs), notably in terms of power losses, voltage variations, and system stability. This paper investigates the optimal placement and sizing of EV charging stations (EVCSs) and DGs under varying EV hosting factors (EV-HFs). An impedance matrix-based load flow method is developed, and a derived analytical formula for power loss calculation is proposed to improve computational efficiency. A weighted multi-objective function is developed to reduce active power losses and voltage variations while optimizing the voltage stability index and the yearly cost savings from energy loss. The optimization is performed using a deterministic heuristic procedure that incrementally adjusts the location and size of EVCSs and DGs until no further improvement in the fitness function is achieved. This stepwise approach provides fast convergence with low computational effort compared to population-based metaheuristics. The methodology is used on the IEEE 33-bus system under different loading conditions and EV-HFs. The results reveal that for 40% and 60% EV-HFs, active power losses decreased by about 57% compared with the basic case, while the minimum bus voltage improved from 0.9148 pu to 0.9654 pu and 0.9641 pu. The economic analysis demonstrates annual savings of up to USD 473,550, with a payback period between 7 and 8 years. These findings emphasize the need of integrated EVCS and DG planning in improving future distribution systems’ technical and economic performance. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

14 pages, 1620 KB

Open AccessArticle

Accelerating High-Entropy Alloy Design via Machine Learning: Predicting Yield Strength from Composition

by Seungtae Lee, Seok Su Sohn, Hae-Seok Lee, Donghwan Kim and Yoonmook Kang

Materials 2026, 19(1), 196; https://doi.org/10.3390/ma19010196 - 5 Jan 2026

Cited by 2 | Viewed by 1774

Abstract

High-entropy alloys (HEAs) have attracted significant attention due to their exceptional physical, chemical, and mechanical properties. The current development of HEAs primarily depends on time-consuming and costly trial-and-error approaches, which not only hinder the efficient exploration of new compositions but also result in [...] Read more.

High-entropy alloys (HEAs) have attracted significant attention due to their exceptional physical, chemical, and mechanical properties. The current development of HEAs primarily depends on time-consuming and costly trial-and-error approaches, which not only hinder the efficient exploration of new compositions but also result in unnecessary resource and energy consumption, thereby negatively affecting sustainable development and production. To address this challenge, this study introduces a machine learning-based methodology for predicting the yield strengths of various HEA compositions. The model was trained using 181 data points and achieved an R² performance score of 0.85. To further assess its reliability and generalization capability, the model was validated using external data not included in the collected dataset. The validation was performed across four categories: modified Cantor alloys, refractory HEAs, eutectic HEAs, and other HEAs. The predicted yield strength trends were found to align with the actual experimental trends, demonstrating the model’s robust performance across various categories of HEAs. The proposed machine learning approach is expected to facilitate the combinatorial design of HEAs, thereby enabling efficient optimization of compositions and accelerating the development of novel alloys. Moreover, it has the potential to serve as a guideline for sustainable alloy design and environmentally conscious production in future HEA development. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

9 pages, 318 KB

Open AccessEditorial

The Nexus of AI and Energy: A Unified Framework for Intelligent Future

by Jaroslaw Krzywanski, Agnieszka Kijo-Kleczkowska, Aleksandar Georgiev, Waqar Muhammad Ashraf, Anas Rao, Iliya Iliev, Jan Taler and Wojciech Nowak

Energies 2026, 19(1), 245; https://doi.org/10.3390/en19010245 - 1 Jan 2026

Viewed by 1266

Abstract

The global energy sector stands at a critical juncture, facing the dual imperative of meeting escalating global energy demand while carrying out urgent decarbonization efforts to combat climate change [...] Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

21 pages, 1745 KB

Open AccessArticle

An Integrated Artificial Intelligence Tool for Predicting and Managing Project Risks

by Andreea Geamanu, Maria-Iuliana Dascalu, Ana-Maria Neagu and Raluca Ioana Guica

Mach. Learn. Knowl. Extr. 2026, 8(1), 1; https://doi.org/10.3390/make8010001 - 20 Dec 2025

Cited by 1 | Viewed by 2407

Abstract

Artificial Intelligence (AI) is increasingly used to enhance project management practices, especially in risk analysis, where traditional tools often lack predictive capabilities. This study introduces an AI-based tool that supports project teams in identifying and interpreting risks through machine learning and integrated documentation [...] Read more.

Artificial Intelligence (AI) is increasingly used to enhance project management practices, especially in risk analysis, where traditional tools often lack predictive capabilities. This study introduces an AI-based tool that supports project teams in identifying and interpreting risks through machine learning and integrated documentation features. A synthetic dataset of 5000 project instances was generated using deterministic rules across 27 input variables, enabling the training of multi-output Decision Tree and Random Forest models to predict risk type, impact, probability, and response strategy. Due to the rule-based structure of the dataset, both models achieved near-perfect classification performance, with Random Forest showing slightly better regression accuracy. These results validate the modelling pipeline but should not be interpreted as real-world predictive accuracy. The trained models were deployed within a web platform offering prediction visualization, automated PDF reporting, result storage, and access to a structured risk management plan template. Survey feedback highlights strong user interest in AI-assisted mitigation suggestions, dashboards, notifications, and mobile access. The findings demonstrate the potential of AI to improve proactive risk assessment and decision-making in project environments. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

22 pages, 23477 KB

Open AccessArticle

FPGA-Accelerated ESN with Chaos Training for Financial Time Series Prediction

by Zeinab A. Hassaan, Mohammed H. Yacoub and Lobna A. Said

Mach. Learn. Knowl. Extr. 2025, 7(4), 160; https://doi.org/10.3390/make7040160 - 3 Dec 2025

Cited by 2 | Viewed by 1843

Abstract

Improving financial time series forecasting presents challenges because models often struggle to identify diverse fault patterns in unseen data. This issue is critical in fintech, where accurate and reliable forecasting of financial data is essential for effective risk management and informed investment strategies. [...] Read more.

Improving financial time series forecasting presents challenges because models often struggle to identify diverse fault patterns in unseen data. This issue is critical in fintech, where accurate and reliable forecasting of financial data is essential for effective risk management and informed investment strategies. This work addresses these challenges by initializing the weights and biases of two proposed models, Gated Recurrent Units (GRUs) and the Echo State Network (ESN), with different chaotic sequences to enhance prediction accuracy and capabilities. We compare reservoir computing (RC) and recurrent neural network (RNN) models with and without the integration of chaotic systems, utilizing standard initialization. The models are validated on six different datasets, including the 500 largest publicly traded companies in the US (S&P500), the Irish Stock Exchange Quotient (ISEQ) dataset, the XAU and USD forex pair (XAU/USD), the USD and JPY forex pair with respect to the currency exchange rate (USD/JPY), Chinese daily stock prices, and the top 100 index of UK companies (FTSE 100). The ESN model, combined with the Lorenz system, achieves the lowest error among other models, reinforcing the effectiveness of chaos-trained models for prediction. The proposed ESN model, accelerated by the Kintex-Ultrascale KCU105 FPGA board, achieves a maximum frequency of

83.5

MHz and a power consumption of

0.677

W. The results of the hardware simulation align with MATLAB R2025b fixed-point analysis. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

23 pages, 1028 KB

Open AccessArticle

A Hybrid Machine Learning Framework for Electricity Fraud Detection: Integrating Isolation Forest and XGBoost for Real-World Utility Data

by Thomas Vitor P. Monteiro, Glaucio José Bezerra Cavalcante Castor, Carlos Gilmer Castillo Correa, Hector Raul Chavez Arias, Dionicio Zócimo Ñaupari Huatuco and Yuri Percy Molina Rodriguez

Energies 2025, 18(23), 6249; https://doi.org/10.3390/en18236249 - 28 Nov 2025

Cited by 2 | Viewed by 1710

Abstract

This paper proposes a hybrid machine learning framework for detecting electricity fraud within the broader context of Non-Technical Losses (NTLs) in power-distribution systems. The framework combines unsupervised anomaly detection using Isolation Forest with supervised classification through XGBoost, exploiting the complementary strengths of both [...] Read more.

This paper proposes a hybrid machine learning framework for detecting electricity fraud within the broader context of Non-Technical Losses (NTLs) in power-distribution systems. The framework combines unsupervised anomaly detection using Isolation Forest with supervised classification through XGBoost, exploiting the complementary strengths of both algorithms. Using real consumption data from a Peruvian utility, the approach integrates domain-informed feature engineering to capture behavioral, temporal, and contextual indicators of irregular usage. To address the extreme class imbalance inherent to fraud datasets, the SMOTETomek hybrid resampling technique was applied, enhancing minority-class representation and decision boundary clarity. Experimental results achieved high predictive performance on the test set (AUC-ROC = 0.999, F1-score = 0.77) using an optimized decision threshold of 0.6. Moreover, SHAP-based interpretability analysis identified extreme monthly variations, prolonged low-consumption periods, and tariff category as key behavioral predictors of fraudulent activity. The robustness of the proposed framework was further validated through a 5-fold cross-validation procedure during the training phase, ensuring consistent performance across different data partitions. Overall, the proposed framework demonstrates not only robust and explainable performance but also practical operational value, providing utilities with a scalable data-driven tool to optimize inspection strategies and maximize recovery of non-technical losses. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

25 pages, 5793 KB

Open AccessArticle

Optimizing Reservoir Characterization with Machine Learning: Predicting Coal Texture Types for Improved Gas Migration and Accumulation Analysis

by Yuting Wang, Cong Zhang, Yahya Wahib, Yanhui Yang, Mengxi Li, Guangjie Sang, Ruiqiang Yang, Jiale Chen, Baolin Yang, Al Dawood Riadh and Jiaren Ye

Energies 2025, 18(23), 6185; https://doi.org/10.3390/en18236185 - 26 Nov 2025

Viewed by 714

Abstract

Coal texture is an important factor in optimizing the characterization of coalbed methane (CBM) reservoirs, directly affecting key reservoir properties such as permeability, gas content, and production potential. This study develops an advanced methodology for coal texture classification in the Zhengzhuang Field of [...] Read more.

Coal texture is an important factor in optimizing the characterization of coalbed methane (CBM) reservoirs, directly affecting key reservoir properties such as permeability, gas content, and production potential. This study develops an advanced methodology for coal texture classification in the Zhengzhuang Field of the Qinshui Basin, utilizing well-log data from 86 wells. Initially, 13 geophysical logging parameters were used to characterize the coal seams, resulting in a dataset comprising 2992 data points categorized into Undeformed Coal (UC), Cataclastic Coal (CC), and Granulated Coal (GC) types. After optimizing and refining the data, the dataset was reduced to 8 parameters, then further narrowed to 5 key features for model evaluation. Two primary scenarios were investigated: Scenario 1 included all 8 parameters, while Scenario 2 focused on the 5 most influential features. Five machine learning classifiers Extra Trees, Gradient Boosting, Support Vector Classifier (SVC), Random Forest, and k-Nearest Neighbors (kNN) were applied to classify coal textures. The Extra Trees classifier outperformed all other models, achieving the highest performance across both scenarios. Its peak performance was observed when 20% of the data was used for the test set and 80% for training, where it achieved a Macro F1 Score of 0.998. These findings demonstrate the potential of machine learning for improving coal texture prediction, offering valuable insights into reservoir characterization and enhancing the understanding of gas migration and accumulation processes. This methodology has significant implications for optimizing CBM resource evaluation and extraction strategies, especially in regions with limited sampling availability. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

35 pages, 904 KB

Open AccessArticle

Clustering-Guided Automatic Generation of Algorithms for the Multidimensional Knapsack Problem

by Cristian Inzulza, Caio Bezares, Franco Cornejo and Victor Parada

Mach. Learn. Knowl. Extr. 2025, 7(4), 144; https://doi.org/10.3390/make7040144 - 12 Nov 2025

Cited by 1 | Viewed by 1591

Abstract

We propose a hybrid framework that integrates instance clustering with Automatic Generation of Algorithms (AGA) to produce specialized algorithms for classes of Multidimensional Knapsack Problem (MKP) instances. This approach is highly relevant given the latest trends in AI, where Large Language Models (LLMs) [...] Read more.

We propose a hybrid framework that integrates instance clustering with Automatic Generation of Algorithms (AGA) to produce specialized algorithms for classes of Multidimensional Knapsack Problem (MKP) instances. This approach is highly relevant given the latest trends in AI, where Large Language Models (LLMs) are actively being used to automate and refine algorithm design through evolutionary frameworks. Our method utilizes a feature-based representation of 328 MKP instances and evaluates K-means, HDBSCAN, and random clustering to produce 11 clusters per method. For each cluster, a master optimization problem was solved using Genetic Programming, evolving algorithms encoded as syntax trees. Fitness was measured as relative error against known optima, a similar objective to those being tackled in LLM-driven optimization. Experimental and statistical analyses demonstrate that clustering-guided AGA significantly reduces average relative error and accelerates convergence compared with AGA trained on randomly grouped instances. K-means produced the most consistent cluster-specialization. Cross-cluster evaluation reveals a trade-off between specialization and generalization. The results demonstrate that clustering prior to AGA is a practical preprocessing step for designing automated algorithms in NP-hard combinatorial problems, paving the way for advanced methodologies that incorporate AI techniques. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

21 pages, 13544 KB

Open AccessArticle

Energy-Efficient Last-Mile Logistics Using Resistive Grid Path Planning Methodology (RGPPM)

by Carlos Hernández-Mejía, Delia Torres-Muñoz, Carolina Maldonado-Méndez, Sergio Hernández-Méndez, Everardo Inzunza-González, Carlos Sánchez-López and Enrique Efrén García-Guerrero

Energies 2025, 18(21), 5625; https://doi.org/10.3390/en18215625 - 26 Oct 2025

Cited by 2 | Viewed by 960

Abstract

Last-mile logistics is a critical operational and environmental challenge in urban areas. This paper introduces an intelligent path planning system using the Resistive Grid Path Planning Methodology (RGPPM) to optimize distribution based on energy and environmental metrics. The foundational innovation is the integration [...] Read more.

Last-mile logistics is a critical operational and environmental challenge in urban areas. This paper introduces an intelligent path planning system using the Resistive Grid Path Planning Methodology (RGPPM) to optimize distribution based on energy and environmental metrics. The foundational innovation is the integration of electrical-circuit analogies, modeling the distribution network as a resistive grid where optimal routes emerge naturally as current flows, offering a paradigm shift from conventional algorithms. Using a multi-connected grid with georeferenced resistances, RGPPM estimates minimum and maximum paths for various starting points and multi-agent scenarios. We introduce five key performance indicators (KPIs)—Percentage of Distance Savings (PDS), Coefficient of Savings (CS), Coefficient of Global Savings (CGS), Percentage of Load Imbalance (PLI), and Percentage of Deviation with Multi-Agent (PDM)—to evaluate system performance. Simulations for textbook delivery to 129 schools in the Veracruz–Boca del Río area show that RGPPM significantly reduces travel distances. This leads to substantial savings in energy consumption, CO₂ emissions, and operating costs, particularly with electric vehicles. Finally, the results validate RGPPM as a flexible and scalable strategy for sustainable urban logistics. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

15 pages, 2232 KB

Open AccessArticle

Image-Based Deep Learning for Brain Tumour Transcriptomics: A Benchmark of DeepInsight, Fotomics, and Saliency-Guided CNNs

by Ali Alyatimi, Vera Chung, Muhammad Atif Iqbal and Ali Anaissi

Mach. Learn. Knowl. Extr. 2025, 7(4), 119; https://doi.org/10.3390/make7040119 - 15 Oct 2025

Cited by 1 | Viewed by 1596

Abstract

Classifying brain tumour transcriptomic data is crucial for precision medicine but remains challenging due to high dimensionality and limited interpretability of conventional models. This study benchmarks three image-based deep learning approaches, DeepInsight, Fotomics, and a novel saliency-guided convolutional neural network (CNN), for transcriptomic [...] Read more.

Classifying brain tumour transcriptomic data is crucial for precision medicine but remains challenging due to high dimensionality and limited interpretability of conventional models. This study benchmarks three image-based deep learning approaches, DeepInsight, Fotomics, and a novel saliency-guided convolutional neural network (CNN), for transcriptomic classification. DeepInsight utilises dimensionality reduction to spatially arrange gene features, while Fotomics applies Fourier transforms to encode expression patterns into structured images. The proposed method transforms each single-cell gene expression profile into an RGB image using PCA, UMAP, or t-SNE, enabling CNNs such as ResNet to learn spatially organised molecular features. Gradient-based saliency maps are employed to highlight gene regions most influential in model predictions. Evaluation is conducted on two biologically and technologically different datasets: single-cell RNA-seq from glioblastoma GSM3828672 and bulk microarray data from medulloblastoma GSE85217. Outcomes demonstrate that image-based deep learning methods, particularly those incorporating saliency guidance, provide a robust and interpretable framework for uncovering biologically meaningful patterns in complex high-dimensional omics data. For instance, ResNet-18 achieved the highest accuracy of 97.25% on the GSE85217 dataset and 91.02% on GSM3828672, respectively, outperforming other baseline models across multiple metrics. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

22 pages, 3708 KB

Open AccessArticle

Faithful Narratives from Complex Conceptual Models: Should Modelers or Large Language Models Simplify Causal Maps?

by Tyler J. Gandee and Philippe J. Giabbanelli

Mach. Learn. Knowl. Extr. 2025, 7(4), 116; https://doi.org/10.3390/make7040116 - 7 Oct 2025

Cited by 1 | Viewed by 1676

Abstract

(1) Background: Comprehensive conceptual models can result in complex artifacts, consisting of many concepts that interact through multiple mechanisms. This complexity can be acceptable and even expected when generating rich models, for instance to support ensuing analyses that find central concepts or decompose [...] Read more.

(1) Background: Comprehensive conceptual models can result in complex artifacts, consisting of many concepts that interact through multiple mechanisms. This complexity can be acceptable and even expected when generating rich models, for instance to support ensuing analyses that find central concepts or decompose models into parts that can be managed by different actors. However, complexity can become a barrier when the conceptual model is used directly by individuals. A ‘transparent’ model can support learning among stakeholders (e.g., in group model building) and it can motivate the adoption of specific interventions (i.e., using a model as evidence base). Although advances in graph-to-text generation with Large Language Models (LLMs) have made it possible to transform conceptual models into textual reports consisting of coherent and faithful paragraphs, turning a large conceptual model into a very lengthy report would only displace the challenge. (2) Methods: We experimentally examine the implications of two possible approaches: asking the text generator to simplify the model, either via abstractive (LLMs) or extractive summarization, or simplifying the model through graph algorithms and then generating the complete text. (3) Results: We find that the two approaches have similar scores on text-based evaluation metrics including readability and overlap scores (ROUGE, BLEU, Meteor), but faithfulness can be lower when the text generator decides on what is an interesting fact and is tasked with creating a story. These automated metrics capture textual properties, but they do not assess actual user comprehension, which would require an experimental study with human readers. (4) Conclusions: Our results suggest that graph algorithms may be preferable to support modelers in scientific translations from models to text while minimizing hallucinations. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

44 pages, 6909 KB

Open AccessArticle

Multi-Objective Optimization of Off-Grid Hybrid Renewable Energy Systems for Sustainable Agricultural Development in Sub-Saharan Africa

by Tom Cherif Bilio, Mahamat Adoum Abdoulaye and Sebastian Waita

Energies 2025, 18(19), 5058; https://doi.org/10.3390/en18195058 - 23 Sep 2025

Cited by 3 | Viewed by 1718 | Correction

Abstract

This study presents a novel multi-objective optimization (MOO) model for the design of an off-grid hybrid renewable energy system (HRES) to support sustainable agriculture and rural development in Sub-Saharan Africa (SSA). Based upon a case study selected in Linia (Chad), three system architectures [...] Read more.

This study presents a novel multi-objective optimization (MOO) model for the design of an off-grid hybrid renewable energy system (HRES) to support sustainable agriculture and rural development in Sub-Saharan Africa (SSA). Based upon a case study selected in Linia (Chad), three system architectures are compared under different levels of the reliability requirements (LPSP = 1%, 5%, and 10%). A Multi-Objective Particle Swarm Optimization (MOPSO) algorithm is applied to optimize the Levelized Cost of Energy (LCOE), CO₂ emissions mitigation, and social impact, referring to the Human Development Index (HDI) enhancement and the job creation (JC) opportunity, using the MATLAB R2024b environment. The calculation results show that among the three configuration schemes, the PV–Wind–Battery configuration obtains the optimal techno–economic–environmental coordination, with the lowest LCOE (0.0948 $/kWh) and the largest CO₂ emission reduction (9.58 × 10⁸ kg), and the Wind–Battery system gets the most social benefit. The method developed provides users with a decision-support method for renewable energy systems (RES) integration into rural agricultural settings, taking into consideration financial cost, environmental sustainability, and community development. This information is important for policymakers and practitioners advocating for decentralized, socially inclusive clean energy access initiatives in underserved regions. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

17 pages, 650 KB

Open AccessEditor’s ChoiceArticle

Optimization of Biomass Delivery Through Artificial Intelligence Techniques

by Marta Wesolowska, Dorota Żelazna-Jochim, Krystian Wisniewski, Jaroslaw Krzywanski, Marcin Sosnowski and Wojciech Nowak

Energies 2025, 18(18), 5028; https://doi.org/10.3390/en18185028 - 22 Sep 2025

Cited by 3 | Viewed by 1535

Abstract

Efficient and cost-effective biomass logistics remain a significant challenge due to the dynamic and nonlinear nature of supply chains, as well as the scarcity of comprehensive data on this topic. As biomass plays an increasingly important role in sustainable energy systems, managing its [...] Read more.

Efficient and cost-effective biomass logistics remain a significant challenge due to the dynamic and nonlinear nature of supply chains, as well as the scarcity of comprehensive data on this topic. As biomass plays an increasingly important role in sustainable energy systems, managing its complex supply chains efficiently is crucial. Traditional logistics methods often struggle with the dynamic, nonlinear, and data-scarce nature of biomass supply, especially when integrating local and international sources. To address these challenges, this study aims to develop an innovative modular artificial neural network (ANN)-based Biomass Delivery Management (BDM) model to optimize biomass procurement and supply for a fluidized bed combined heat and power (CHP) plant. The comprehensive model integrates technical, economic, and geographic parameters to enable supplier selection, optimize transport routes, and inform fuel blending strategies, representing a novel approach in biomass logistics. A case study based on operational data confirmed the model’s ability to identify cost-effective and quality-compliant biomass sources. Evaluated using empirical operational data from a Polish CHP plant, the ANN-based model demonstrated high predictive accuracy (MAE = 0.16, MSE = 0.02, R² = 0.99) within the studied scope. The model effectively handled incomplete datasets typical of biomass markets, aiding in supplier selection decisions and representing a proof-of-concept for optimizing Central European biomass logistics. The model was capable of generalizing supplier recommendations based on input variables, including biomass type, unit price, and annual demand. The proposed framework supports both strategic and real-time logistics decisions, providing a robust tool for enhancing supply chain transparency, cost efficiency, and resilience in the renewable energy sector. Future research will focus on extending the dataset and developing hybrid models to strengthen supply chain stability and adaptability under varying market and regulatory conditions. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

15 pages, 2477 KB

Open AccessArticle

Non-Destructive Surface Characterization Using Microscopic Imaging and Data Modeling

by Mariusz Mączka, Maciej Kusy, Anna Szlachta and Ewa Korzeniewska

Materials 2025, 18(18), 4376; https://doi.org/10.3390/ma18184376 - 19 Sep 2025

Cited by 1 | Viewed by 876

Abstract

This article presents a novel method for converting a digital image of a conductive surface into its three-dimensional spatial representation. The developed approach utilizes a mathematical transformation of pixel intensity to the height value of the represented point. The method includes interpolation, automatic [...] Read more.

This article presents a novel method for converting a digital image of a conductive surface into its three-dimensional spatial representation. The developed approach utilizes a mathematical transformation of pixel intensity to the height value of the represented point. The method includes interpolation, automatic image segmentation, and predictive reconstruction of surface profiles, which significantly improves the quality of material surface representation. The method was implemented in a 3D model of a conductive structure created in the physical vacuum deposition method, and its capabilities were demonstrated using examples of simulations of the electric field distribution within and on the surface of the tested sample. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

38 pages, 2993 KB

Open AccessArticle

CRISP-NET: Integration of the CRISP-DM Model with Network Analysis

by Héctor Alejandro Acuña-Cid, Eduardo Ahumada-Tello, Óscar Omar Ovalle-Osuna, Richard Evans, Julia Elena Hernández-Ríos and Miriam Alondra Zambrano-Soto

Mach. Learn. Knowl. Extr. 2025, 7(3), 101; https://doi.org/10.3390/make7030101 - 16 Sep 2025

Cited by 2 | Viewed by 3906

Abstract

To carry out data analysis, it is necessary to implement a model that guides the process in an orderly and sequential manner, with the aim of maintaining control over software development and its documentation. One of the most widely used tools in the [...] Read more.

To carry out data analysis, it is necessary to implement a model that guides the process in an orderly and sequential manner, with the aim of maintaining control over software development and its documentation. One of the most widely used tools in the field of data analysis is the Cross-Industry Standard Process for Data Mining (CRISP-DM), which serves as a reference framework for data mining, allowing the identification of patterns and, based on them, supporting informed decision-making. Another tool used for pattern identification and the study of relationships within systems is network analysis (NA), which makes it possible to explore how different components are interconnected. The integration of these tools can be justified and developed under the principles of Situational Method Engineering (SME), which allows for the adaptation and customization of existing methods according to the specific needs of a problem or context. Through SME, it is possible to determine which components of CRISP-DM need to be adjusted to efficiently incorporate NA, ensuring that this integration aligns with the project’s objectives in a structured and effective manner. The proposed methodological process was applied in a real working group, which allowed its functionality to be validated, each phase to be documented, and concrete outputs to be generated, demonstrating its usefulness for the development of analytical projects. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

14 pages, 1259 KB

Open AccessArticle

MCTS-Based Policy Improvement for Reinforcement Learning

by György Csippán, István Péter, Bálint Kővári and Tamás Bécsi

Mach. Learn. Knowl. Extr. 2025, 7(3), 98; https://doi.org/10.3390/make7030098 - 10 Sep 2025

Cited by 1 | Viewed by 3130

Abstract

Curriculum Learning (CL) is a potent field in Machine Learning that provides several excellent techniques for enhancing the performance of the training process given the same data points, regardless of the training method used. In this research, we propose a novel Monte Carlo [...] Read more.

Curriculum Learning (CL) is a potent field in Machine Learning that provides several excellent techniques for enhancing the performance of the training process given the same data points, regardless of the training method used. In this research, we propose a novel Monte Carlo Tree Search (MCTS)-based technique that enhances model performance, articulating the utilization of MCTS in Curriculum Learning. The proposed approach leverages MCTS to optimize the sequence of batches during the training process. First, we demonstrate the application of our method in Reinforcement Learning, where sparse rewards often diminish convergence and deteriorate performance. By leveraging the strategic planning and exploration capabilities of MCTS, our method systematically identifies and selects trajectories that are more informative and have a higher potential to enhance policy improvement. This MCTS-guided batch optimization focuses the learning process on valuable experiences, accelerating convergence and improving overall performance. We evaluate our approach on standard RL benchmarks, demonstrating that it outperforms conventional batch selection methods regarding learning speed and policy effectiveness. The results highlight the potential of combining MCTS with CL to optimize batch selection, offering a promising direction for future research in efficient Reinforcement Learning. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

22 pages, 3865 KB

Open AccessArticle

AI-Based Prediction-Driven Control Framework for Hydrogen–Natural Gas Blends in Natural Gas Networks

by George Calianu, Ștefan-Ionuț Spiridon, Andrei-Catalin Militaru, Antoaneta Roman, Marius Constantinescu, Felicia Bucura, Roxana Elena Ionete and Eusebiu Ilarian Ionete

Energies 2025, 18(18), 4799; https://doi.org/10.3390/en18184799 - 9 Sep 2025

Cited by 3 | Viewed by 1339

Abstract

This study presents the development and implementation of an AI-driven control system for dynamic regulation of hydrogen blending in natural gas networks. Leveraging supervised machine learning techniques, a Random Forest Classifier was trained to accurately identify the origin of gas blends based on [...] Read more.

This study presents the development and implementation of an AI-driven control system for dynamic regulation of hydrogen blending in natural gas networks. Leveraging supervised machine learning techniques, a Random Forest Classifier was trained to accurately identify the origin of gas blends based on compositional fingerprints, achieving rapid inference suitable for real-time applications. Concurrently, a Random Forest Regression model was developed to estimate the optimal hydrogen flow rate required to meet a user-defined higher calorific value target, demonstrating exceptional predictive accuracy with a mean absolute error of 0.0091 Nm³ and a coefficient of determination (R²) of 0.9992 on test data. The integrated system, deployed via a Streamlit-based graphical interface, provides continuous real-time adjustments of gas composition, alongside detailed physicochemical property estimation and emission metrics. Validation through comparative analysis of predicted versus actual hydrogen flow rates confirms the robustness and generalizability of the approach under both simulated and operational conditions. The proposed framework enhances operational transparency and economic efficiency by enabling adaptive blending control and automatic source identification, thereby facilitating optimized fuel quality management and compliance with industrial standards. This work contributes to advancing smart combustion technologies and supports the sustainable integration of renewable hydrogen in existing gas infrastructures. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

28 pages, 2702 KB

Open AccessArticle

An Overview of the Euler-Type Universal Numerical Integrator (E-TUNI): Applications in Non-Linear Dynamics and Predictive Control

by Paulo M. Tasinaffo, Gildárcio S. Gonçalves, Johnny C. Marques, Luiz A. V. Dias and Adilson M. da Cunha

Algorithms 2025, 18(9), 562; https://doi.org/10.3390/a18090562 - 4 Sep 2025

Cited by 1 | Viewed by 1179

Abstract

A Universal Numerical Integrator (UNI) is a computational framework that combines a classical numerical integration method, such as Euler, Runge–Kutta, or Adams–Bashforth, with a universal approximator of functions, such as a feed-forward neural network (including MLP, SVM, RBF, among others) or a fuzzy [...] Read more.

A Universal Numerical Integrator (UNI) is a computational framework that combines a classical numerical integration method, such as Euler, Runge–Kutta, or Adams–Bashforth, with a universal approximator of functions, such as a feed-forward neural network (including MLP, SVM, RBF, among others) or a fuzzy inference system. The Euler-Type Universal Numerical Integrator (E–TUNI) is a particular case of UNI based on the first-order Euler integrator and is designed to model non-linear dynamic systems observed in real-world scenarios accurately. The UNI framework can be organized into three primary methodologies: the NARMAX model (Non-linear AutoRegressive Moving Average with eXogenous input), the mean derivatives approach (which characterizes E–TUNI), and the instantaneous derivatives approach. The E–TUNI methodology relies exclusively on mean derivative functions, distinguishing it from techniques that employ instantaneous derivatives. Although it is based on a first-order scheme, the E–TUNI achieves an accuracy level comparable to that of higher-order integrators. This performance is made possible by the incorporation of a neural network acting as a universal approximator, which significantly reduces the approximation error. This article provides a comprehensive overview of the E–TUNI methodology, focusing on its application to the modeling of non-linear autonomous dynamic systems and its use in predictive control. Several computational experiments are presented to illustrate and validate the effectiveness of the proposed method. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

27 pages, 33734 KB

Open AccessArticle

Full Domain Analysis in Fluid Dynamics

by Alexander Hagg, Adam Gaier, Dominik Wilde, Alexander Asteroth, Holger Foysi and Dirk Reith

Mach. Learn. Knowl. Extr. 2025, 7(3), 86; https://doi.org/10.3390/make7030086 - 18 Aug 2025

Viewed by 1955

Abstract

Novel techniques in evolutionary optimization, simulation, and machine learning enable a broad analysis of domains like fluid dynamics, in which computation is expensive and flow behavior is complex. This paper introduces the concept of full domain analysis, defined as the ability to efficiently [...] Read more.

Novel techniques in evolutionary optimization, simulation, and machine learning enable a broad analysis of domains like fluid dynamics, in which computation is expensive and flow behavior is complex. This paper introduces the concept of full domain analysis, defined as the ability to efficiently determine the full space of solutions in a problem domain and analyze the behavior of those solutions in an accessible and interactive manner. The goal of full domain analysis is to deepen our understanding of domains by generating many examples of flow, their diversification, optimization, and analysis. We define a formal model for full domain analysis, its current state of the art, and the requirements of its sub-components. Finally, an example is given to show what can be learned by using full domain analysis. Full domain analysis, rooted in optimization and machine learning, can be a valuable tool in understanding complex systems in computational physics and beyond. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Graphical abstract

29 pages, 9069 KB

Open AccessArticle

Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration

by Gökhan Deveci, Özgün Yücel and Ali Bahadır Olcay

Energies 2025, 18(14), 3783; https://doi.org/10.3390/en18143783 - 17 Jul 2025

Viewed by 1560

Abstract

This study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled with the SST [...] Read more.

This study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled with the SST k-ω turbulence model. The first approach employs a fully connected dense neural network to directly map scalar input parameters—fuel velocity, swirl ratio, and equivalence ratio—to high-resolution temperature contour images. In addition, a comparison was made with different deep learning networks, namely Res-Net, EfficientNetB0, and Inception Net V3, to better understand the performance of the model. In the first approach, the results of the Inception V3 model and the developed Dense Model were found to be better than Res-Net and Efficient Net. At the same time, file sizes and usability were examined. The second framework employs a U-Net-based convolutional neural network enhanced by an RGB Fusion preprocessing technique, which integrates multiple scalar fields from non-reacting (cold flow) conditions into composite images, significantly improving spatial feature extraction. The training and validation processes for both models were conducted using 80% of the CFD data for training and 20% for testing, which helped assess their ability to generalize new input conditions. In the secondary approach, similar to the first approach, studies were conducted with different deep learning models, namely Res-Net, Efficient Net, and Inception Net, to evaluate model performance. The U-Net model, which is well developed, stands out with its low error and small file size. The dense network is appropriate for direct parametric analyses, while the image-based U-Net model provides a rapid and scalable option to utilize the cold flow CFD images. This framework can be further refined in future research to estimate more flow factors and tested against experimental measurements for enhanced applicability. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

23 pages, 963 KB

Open AccessArticle

A Methodology for Turbine-Level Possible Power Prediction and Uncertainty Estimations Using Farm-Wide Autoregressive Information on High-Frequency Data

by Francisco Javier Jara Ávila, Timothy Verstraeten, Pieter Jan Daems, Ann Nowé and Jan Helsen

Energies 2025, 18(14), 3764; https://doi.org/10.3390/en18143764 - 16 Jul 2025

Cited by 2 | Viewed by 898

Abstract

Wind farm performance monitoring has traditionally relied on deterministic models, such as power curves or machine learning approaches, which often fail to account for farm-wide behavior and the uncertainty quantification necessary for the reliable detection of underperformance. To overcome these limitations, we propose [...] Read more.

Wind farm performance monitoring has traditionally relied on deterministic models, such as power curves or machine learning approaches, which often fail to account for farm-wide behavior and the uncertainty quantification necessary for the reliable detection of underperformance. To overcome these limitations, we propose a probabilistic methodology for turbine-level active power prediction and uncertainty estimation using high-frequency SCADA data and farm-wide autoregressive information. The method leverages a Stochastic Variational Gaussian Process with a Linear Model of Coregionalization, incorporating physical models like manufacturer power curves as mean functions and enabling flexible modeling of active power and its associated variance. The approach was validated on a wind farm in the Belgian North Sea comprising over 40 turbines, using only 15 days of data for training. The results demonstrate that the proposed method improves predictive accuracy over the manufacturer’s power curve, achieving a reduction in error measurements of around 1%. Improvements of around 5% were seen in dominant wind directions (200°–300°) using 2 and 3 Latent GPs, with similar improvements observed on the test set. The model also successfully reconstructs wake effects, with Energy Ratio estimates closely matching SCADA-derived values, and provides meaningful uncertainty estimates and posterior turbine correlations. These results demonstrate that the methodology enables interpretable, data-efficient, and uncertainty-aware turbine-level power predictions, suitable for advanced wind farm monitoring and control applications, enabling a more sensitive underperformance detection. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

30 pages, 4318 KB

Open AccessEditor’s ChoiceArticle

AI-Enhanced Photovoltaic Power Prediction Under Cross-Continental Dust Events and Air Composition Variability in the Mediterranean Region

by Pavlos Nikolaidis

Energies 2025, 18(14), 3731; https://doi.org/10.3390/en18143731 - 15 Jul 2025

Cited by 2 | Viewed by 1386

Abstract

Accurate short-term forecasting of photovoltaic power generation is vital for the operational stability of isolated energy systems, especially in regions with increasing renewable energy penetration. This study presents a novel AI-based forecasting framework applied to the island of Cyprus. Using machine learning methods, [...] Read more.

Accurate short-term forecasting of photovoltaic power generation is vital for the operational stability of isolated energy systems, especially in regions with increasing renewable energy penetration. This study presents a novel AI-based forecasting framework applied to the island of Cyprus. Using machine learning methods, particularly regression trees, the proposed approach evaluates the impact of key environmental variables on PV performance, with an emphasis on atmospheric dust transport and air composition variability. A distinguishing feature of this work is the integration of cross-continental dust events and diverse atmospheric parameters into a structured forecasting model. A new clustering methodology is introduced to classify these inputs and analyze their correlation with PV output, enabling improved feature selection for model training. Importantly, all input parameters are sourced from publicly accessible, internet-based platforms, facilitating wide reproducibility and operational application. The obtained results demonstrate that incorporating dust deposition and air composition features significantly enhances forecasting accuracy, particularly during severe dust episodes. This research not only fills a notable gap in the PV forecasting literature but also provides a scalable model for other dust-prone regions transitioning to high levels of solar energy integration. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

25 pages, 875 KB

Open AccessEditor’s ChoiceArticle

Filter Learning-Based Partial Least Squares Regression and Its Application in Infrared Spectral Analysis

by Yi Mou, Long Zhou, Weizhen Chen, Jianguo Liu and Teng Li

Algorithms 2025, 18(7), 424; https://doi.org/10.3390/a18070424 - 9 Jul 2025

Cited by 3 | Viewed by 1997

Abstract

Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel [...] Read more.

Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel filter learning-based PLS (FPLS) model that integrates an adaptive filter into the PLS framework. The FPLS model is designed to maximize the covariance between the filtered spectral data and the response. This modification enables FPLS to dynamically adapt to the characteristics of the data, thereby enhancing its feature extraction and noise suppression capabilities. We have developed an efficient algorithm to solve the FPLS optimization problem and provided theoretical analyses regarding the convergence of the model, the prediction variance, and the relationships among the objective functions of FPLS, PLS, and the filter length. Furthermore, we have derived bounds for the Root Mean Squared Error of Prediction (RMSEP) and the Cosine Similarity (CS) to evaluate model performance. Experimental results using spectral datasets from Corn, Octane, Mango, and Soil Nitrogen show that the FPLS model outperforms PLS, OSCPLS, VCPLS, PoPLS, LoPLS, DOSC, OPLS, MSC, SNV, SGFilter, and Lasso in terms of prediction accuracy. The theoretical analyses align with the experimental results, emphasizing the effectiveness and robustness of the FPLS model in managing complex spectral data. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

28 pages, 5208 KB

Open AccessEditor’s ChoiceArticle

The Use of BIM Models and Drone Flyover Data in Building Energy Efficiency Analysis

by Agata Muchla, Małgorzata Kurcjusz, Maja Sutkowska, Raquel Burgos-Bayo, Eugeniusz Koda and Anna Stefańska

Energies 2025, 18(13), 3225; https://doi.org/10.3390/en18133225 - 20 Jun 2025

Cited by 6 | Viewed by 2964

Abstract

Building information modeling (BIM) and thermal imaging from drone flyovers present innovative opportunities for enhancing building energy efficiency. This study examines the integration of BIM models with thermal data collected using unmanned aerial vehicles (UAVs) to assess and manage energy performance throughout a [...] Read more.

Building information modeling (BIM) and thermal imaging from drone flyovers present innovative opportunities for enhancing building energy efficiency. This study examines the integration of BIM models with thermal data collected using unmanned aerial vehicles (UAVs) to assess and manage energy performance throughout a building’s lifecycle. By leveraging BIM’s structured data and the concept of the digital twin, thermal analysis can be automated to detect thermal bridges and inefficiencies, facilitating data-driven decision-making in sustainable construction. The paper examines methodologies for combining thermal imaging with BIM, including image analysis algorithms and artificial intelligence applications. Case studies demonstrate the practical implementation of UAV-based thermal data collection and BIM integration in an educational facility. The findings highlight the potential for optimizing energy efficiency, improving facility management, and advancing low-emission building practices. The study also addresses key challenges such as data standardization and interoperability, and outlines future research directions in the context of smart city applications and energy-efficient urban development. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

14 pages, 2109 KB

Open AccessArticle

XGBoost-Based Modeling of Electrocaloric Property: A Bayesian Optimization in BCZT Electroceramics

by Mustafa Cagri Bayir and Ebru Mensur

Materials 2025, 18(12), 2682; https://doi.org/10.3390/ma18122682 - 6 Jun 2025

Cited by 2 | Viewed by 1179

Abstract

Electrocaloric materials, which exhibit adiabatic temperature change under an applied electric field, are promising for solid-state cooling technologies. In this study, the electrocaloric response of lead-free Ba_xCa_1−xZr_yTi_1−yO₃ (BCZT) ceramics was modeled to investigate the [...] Read more.

Electrocaloric materials, which exhibit adiabatic temperature change under an applied electric field, are promising for solid-state cooling technologies. In this study, the electrocaloric response of lead-free Ba_xCa_1−xZr_yTi_1−yO₃ (BCZT) ceramics was modeled to investigate the effects of composition, processing, and measurement conditions on performance. A high-accuracy XGBoost regression model (R² = 0.99, MAE = 0.02 °C) was developed using a dataset of 2188 literature-derived data points to predict and design the electrocaloric response of BCZT ceramics. The feature space incorporated compositional ratios, processing parameters, measurement settings, and atomic-level Magpie descriptors, along with Curie temperature to account for phase-transition behavior. Feature importance analysis revealed that electric field, measurement temperature, and proximity to the Curie point are the most critical factors influencing ΔT_EC. Bayesian optimization was applied to navigate the design space and identify performance maxima under unconstrained and realistic constraints, offering valuable insights into the nonlinear interactions governing electrocaloric performance. Under room temperature and moderate-field conditions (24 °C, 40 kV/cm), the optimized ΔT_EC achieved a value of 1.03 °C for Ba_0.85Ca_0.15Zr_0.40Ti_0.60, to be processed at 1090 °C for 3 h during calcination, 1300 °C for 2 h during sintering. By integrating experimental insight with machine learning and optimization, this study offers a refined, interpretable framework for accelerating the design of high-performance electrocaloric ceramics while reducing the experimental workload. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

20 pages, 2328 KB

Open AccessArticle

Adaptive Multitask Neural Network for High-Fidelity Wake Flow Modeling of Wind Farms

by Dichang Zhang, Christian Santoni, Zexia Zhang, Dimitris Samaras and Ali Khosronejad

Energies 2025, 18(11), 2897; https://doi.org/10.3390/en18112897 - 31 May 2025

Cited by 1 | Viewed by 1499

Abstract

Wind turbine wake modeling is critical for the design and optimization of wind farms. Traditional methods often struggle with the trade-off between accuracy and computational cost. Recently, data-driven neural networks have emerged as a promising solution, offering both high fidelity and fast inference [...] Read more.

Wind turbine wake modeling is critical for the design and optimization of wind farms. Traditional methods often struggle with the trade-off between accuracy and computational cost. Recently, data-driven neural networks have emerged as a promising solution, offering both high fidelity and fast inference speeds. To advance this field, a novel machine learning model has been developed to predict wind farm mean flow fields through an adaptive multi-fidelity framework. This model extends transfer-learning-based high-dimensional multi-fidelity modeling to scenarios where varying fidelity levels correspond to distinct physical models, rather than merely differing grid resolutions. Built upon a U-Net architecture and incorporating a wind farm parameter encoder, our framework integrates high-fidelity large-eddy simulation (LES) data with a low-fidelity engineering wake model. By directly predicting time-averaged velocity fields from wind farm parameters, our approach eliminates the need for computationally expensive simulations during inference, achieving real-time performance (

1.32 \times 10^{- 5}

GPU hours per instance with negligible CPU workload). Comparisons against field-measured data demonstrate that the model accurately approximates high-fidelity LES predictions, even when trained with limited high-fidelity data. Furthermore, its end-to-end extensible design allows full differentiability and seamless integration of multiple fidelity levels, providing a versatile and scalable solution for various downstream tasks, including wind farm control co-design. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

39 pages, 4034 KB

Open AccessArticle

Reference Point and Grid Method-Based Evolutionary Algorithm with Entropy for Many-Objective Optimization Problems

by Qi Leng, Bo Shan and Chong Zhou

Entropy 2025, 27(5), 524; https://doi.org/10.3390/e27050524 - 14 May 2025

Cited by 1 | Viewed by 1877

Abstract

In everyday scenarios, there are many challenges involving multi-objective optimization. As the count of objective functions rises to four or beyond, the problem’s complexity intensifies considerably, often making it challenging for traditional algorithms to arrive at satisfactory solutions. The non-dominated sorting evolutionary reference [...] Read more.

In everyday scenarios, there are many challenges involving multi-objective optimization. As the count of objective functions rises to four or beyond, the problem’s complexity intensifies considerably, often making it challenging for traditional algorithms to arrive at satisfactory solutions. The non-dominated sorting evolutionary reference point-based (NSGA-III) and the grid-based evolutionary algorithms (GrEA) are two prevalent algorithms for many-objective optimization. These two algorithms preserve population diversity by employing reference point and grid mechanisms, respectively. However, they still have limitations when addressing many-objective optimization problems. Due to the uniform distribution of reference points, the reference point-based methods do not obtain good performance on problems with an irregular Pareto front, while grid-based methods do not achieve good results on problems with a regular Pareto front because of the uneven partition of grids. To address the limitations of reference point-based algorithms and grid-based approaches in tackling both regular and irregular problems, a reference point- and grid-based evolutionary algorithm with entropy is proposed for many-objective optimization, denoted as RGEA, which aims to solve both regular and irregular many-objective optimization problems. Entropy is introduced to measure the shape of the Pareto front of a many-objective optimization problem. In RGEA, a parameter

α

is introduced to determine the interval for calculating the entropy value. By comparing the current entropy value with the maximum entropy value, the reference point-based method or the grid-based method can be determined. In order to verify the performance of the proposed algorithm, a comprehensive experiment was designed on some popular test suites with 3-to-10 objectives. In addition, RGEA was compared against six algorithms without adaptive technology and six algorithms with adaptive technology. A great number of experimental results were obtained showing that RGEA can obtain good results. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

22 pages, 1543 KB

Open AccessArticle

A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder

by Xingfa Zi, Feiyi Liu, Mingyang Liu and Yang Wang

Energies 2025, 18(10), 2434; https://doi.org/10.3390/en18102434 - 9 May 2025

Cited by 9 | Viewed by 2321

Abstract

Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based [...] Read more.

Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–decoder model, to forecast PV power generation. TiDE compresses historical time series and covariates into latent representations via residual connections and reconstructs future values through a temporal decoder, capturing both long- and short-term dependencies. We trained the model using data from 2020 to 2022 from Australia’s Desert Knowledge Australia Solar Centre (DKASC), with 2023 data used for testing. Forecast accuracy was evaluated using the

R^{2}

coefficient of determination, mean absolute error (MAE), and root mean square error (RMSE). In the 5 min ahead forecasting test, TiDE demonstrated high short-term accuracy with an

R^{2}

of 0.952, MAE of 0.150, and RMSE of 0.349, though performance declines for longer horizons, such as the 1 h ahead forecast, compared to other algorithms. For one-day-ahead forecasts, it achieved an

R^{2}

of 0.712, an MAE of 0.507, and an RMSE of 0.856, effectively capturing medium-term weather trends but showing limited responsiveness to sudden weather changes. Further analysis indicated improved performance in cloudy and rainy weather, and seasonal analysis reveals higher accuracy in spring and autumn, with reduced accuracy in summer and winter due to extreme conditions. Additionally, we explore the TiDE model’s sensitivity to input environmental variables, algorithmic versatility, and the implications of forecasting errors on PV grid integration. These findings highlight TiDE’s superior forecasting accuracy and robust adaptability across weather conditions, while also revealing its limitations under abrupt changes. Full article

(This article belongs to the Topic AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition)

► Show Figures

Figure 1

Topic Menu

Topic Editors

AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition

Topic Information

Keywords

Participating Journals

Published Papers (55 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Topic Menu

Topic Editors

AI and Computational Methods for Modelling, Simulations and Optimizing of Advanced Systems: Innovations in Complexity, 2nd Edition

Topic Information

Keywords

Participating Journals

Related Topic

Published Papers (55 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI