Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence (AI) for Energy Systems

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 October 2025) | Viewed by 14128

Share This Special Issue

Special Issue Editor

Dr. Murphy M. Peksen

E-Mail Website
Guest Editor

Chair of Energy Systems, TUM School of Engineering and Design, Technical University of Munich, Boltzmannstr 15, 85748 Garching bei Munich, Germany
Interests: multiphysics; clean energy and digital technologies

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) is revolutionising green energy systems, finding optimal operation solutions, improved material and component performance, energy efficiency, and enabling smarter decision-making for the progression of different stages of research-based development. In the realm of sustainable energy solutions, AI algorithms process a vast amount of data based on both experimental and numerical methods to predict patterns and parametric relationships, optimise multiphysics efficiency, and manage resources effectively. Physics-based machine learning techniques enable the predictive optimization of processes, reducing downtime and costs. AI-assisted innovative concepts and systems also facilitate the coupling and effective assessment of integrated clean energy technologies. Additionally, human–machine interactions have the potential to develop and evaluate high-performance materials. These advancements not only safely increase reliability and resilience, but they also pave the way for a more sustainable and environmentally friendly energy future, with smaller carbon footprints and fewer wasted resources. AI’s transformative capabilities are promising for addressing complex challenges and driving innovation across transdisciplinary sectors.

Dr. Murphy M. Peksen
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

machine learning
AI
hydrogen
clean energy
optimisation
HP materials
multiphysics

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (6 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

19 pages, 2349 KB

Open AccessArticle

Enhancing Extrapolation of Buckley–Leverett Solutions with Physics-Informed and Transfer-Learned Fourier Neural Operators

by Yangnan Shangguan, Junhong Jia, Ke Wu, Xianlin Ma, Rong Zhong and Zhenzihao Zhang

Appl. Sci. 2025, 15(24), 13005; https://doi.org/10.3390/app152413005 - 10 Dec 2025

Abstract

Accurate modeling of multiphase flow in porous media remains challenging due to the nonlinear transport and sharp displacement fronts described by the Buckley–Leverett (B-L) equation. Although Fourier Neural Operators (FNOs) have recently emerged as powerful surrogates for parametric partial differential equations, they exhibit limited robustness when extrapolating beyond the training regime, particularly for shock-dominated fractional flows. This study aims to enhance the extrapolative performance of FNOs for one-dimensional B-L displacement. Analytical solutions were generated using Welge’s graphical method, and datasets were constructed across a range of mobility ratios. A baseline FNO was trained to predict water saturation profiles and evaluated under both interpolation and extrapolation conditions. While the standard FNO accurately reconstructs saturation profiles within the training window, it misestimates shock positions and saturation jumps when extended to longer times or higher mobility ratios. To address these limitations, we develop Physics-Informed FNOs (PI-FNOs), which embed PDE residuals and boundary constraints, and Transfer-Learned FNOs (TL-FNOs), which adapt pretrained operators to new regimes using limited data. Comparative analyses show that both approaches markedly improve extrapolation accuracy, with PI-FNOs achieving the most consistent and physically reliable performance. These findings demonstrate the potential of combining physics constraints and knowledge transfer for robust operator learning in multiphase flow systems. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Figure 1

32 pages, 5381 KB

Open AccessArticle

Single-Step Allowable Action Threshold Determination of Renewable Energy Automatic Generation Control Using Model-Based and Data-Driven Method

by Ziqi Wang, Gaichao Xue, Yanlou Song, Renkai Liu, Guanghui Chang, Po Wu and Kaifeng Zhang

Appl. Sci. 2025, 15(23), 12408; https://doi.org/10.3390/app152312408 - 22 Nov 2025

Viewed by 264

Abstract

Renewable energy automatic generation control (AGC) has the characteristics of rapid adjustment and flexibility, which play a critical role in frequency regulation. Abnormal outputs in renewable energy AGC may trigger frequency fluctuations and threaten grid security. To address the above problems in renewable energy, AGC, a combined model-based and data-driven method for determining the single-step allowable action threshold, is proposed. Firstly, an AGC model with multiple frequency-regulating units is built, and the threshold can be obtained through simulation considering system status parameters. Secondly, as the model-based method struggles to satisfy the requirement of rapidity, a data-driven model based on CNN-LSTM is employed to determine the threshold in real-time. The training data is provided by a model-based method. Considering the limited coverage and interpretability of neural networks, a statistical error-prevention method is proposed to avoid deviations. Then, an adaptive piecewise constant approximation algorithm is employezd to reduce threshold update frequency and the burden for dispatchers. Finally, an adaptive threshold adjustment method for extreme scenarios is proposed, ensuring the frequency regulation of renewable energy AGC under extreme scenarios. Through experiments, the reliability and validity of the proposed method in threshold determination and error prevention are validated. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Figure 1

24 pages, 9118 KB

Open AccessArticle

Temporal Complementarity Analysis of Photovoltaic and Wind Power Generation Using Dynamic Time Warping

by Arkadiusz Małek, Katarzyna Piotrowska, Michalina Gryniewicz-Jaworska and Andrzej Marciniak

Appl. Sci. 2025, 15(22), 12119; https://doi.org/10.3390/app152212119 - 14 Nov 2025

Viewed by 365

Abstract

This study presents an analysis of the temporal complementarity between photovoltaic and wind power generation based on real measurement data obtained in the Lublin Voivodeship (Poland) in 2024. The main objective of the research was to evaluate the degree of time-dependent interaction between two renewable energy sources and to determine the potential for hybrid operation in a regional renewable energy mix. The measurements were conducted under real operating conditions, with a sampling frequency of 15 min for photovoltaic data and 10 min for wind data. After synchronization and resampling to a common 30 min interval, both datasets were compared using the Dynamic Time Warping (DTW) algorithm, which allows for the nonlinear alignment of time series with phase shifts. The results confirmed significant variability in the relationship between the two sources depending on the month. In April, a higher DTW distance (174.281) indicated the predominance of source substitutability, where one source compensated for the low generation of the other. In May, the DTW distance decreased to 138.978, revealing stronger source complementarity, where both PV and wind contributed simultaneously to the total output. The study demonstrates that DTW is a useful analytical tool for identifying temporal complementarity patterns and for quantifying the synergy between renewable sources. The proposed methodology can be applied to optimize hybrid system design and to improve grid balancing in energy systems with a high share of renewables. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Figure 1

25 pages, 2110 KB

Open AccessArticle

Deep Learning Forecasting Model for Market Demand of Electric Vehicles

by Ahmed Ihsan Simsek, Erdinç Koç, Beste Desticioglu Tasdemir, Ahmet Aksöz, Muammer Turkoglu and Abdulkadir Sengur

Appl. Sci. 2024, 14(23), 10974; https://doi.org/10.3390/app142310974 - 26 Nov 2024

Cited by 7 | Viewed by 6310

Abstract

The increasing demand for electric vehicles (EVs) requires accurate forecasting to support strategic decisions by manufacturers, policymakers, investors, and infrastructure developers. As EV adoption accelerates due to environmental concerns and technological advances, understanding and predicting this demand becomes critical. In light of these considerations, this study presents an innovative methodology for forecasting EV demand. This model, called EVs-PredNet, is developed using deep learning methods such as LSTM (Long Short-Term Memory) and CNNs (Convolutional Neural Networks). The model comprises convolutional, activation function, max pooling, LSTM, and dense layers. Experimental research has investigated four different categories of electric vehicles: battery electric vehicles (BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and all electric vehicles (ALL). Performance measures were calculated after conducting experimental studies to assess the model’s ability to predict electric vehicle demand. When the performance measures (mean absolute error, root mean square error, mean squared error, R-Squared) of EVs-PredNet and machine learning regression methods are compared, the proposed model is more effective than the other forecasting methods. The experimental results demonstrate the effectiveness of the proposed approach in forecasting the electric vehicle demand. This model is considered to have significant application potential in assessing the adoption and demand of electric vehicles. This study aims to improve the reliability of forecasting future demand in the electric vehicle market and to develop relevant approaches. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Figure 1

14 pages, 3398 KB

Open AccessArticle

CFD and Artificial Intelligence-Based Machine Learning Synergy for the Assessment of Syngas-Utilizing Pre-Reformer in r-SOC Technology Advancement

by Murphy M. Peksen

Appl. Sci. 2024, 14(22), 10181; https://doi.org/10.3390/app142210181 - 6 Nov 2024

Cited by 1 | Viewed by 2118

Abstract

This study demonstrates the significant advantages of integrating computational fluid dynamics (CFD) with artificial intelligence (AI)-based machine learning (ML) to optimize the pre-reforming process for reversible solid oxide cell (r-SOC) technologies. It places a distinct focus on the relationship between process variables, aiming to enhance the preparation of quality r-SOC-ready fuel, which is an indispensable element for successful operation. Evaluating the intricate thermochemistry of syngas-containing reforming processes involves employing an experimentally validated CFD model. The model serves as the foundation for gathering essential data, crucial for the development and training of AI-based machine learning models. The developed model forecasts and optimizes reforming processes across diverse fuel compositions, encompassing oxygen-containing syngas blends and controlled feedstock outlet process conditions. Impressively, the model’s predictions align closely with CFD outcomes with an error margin as low as 0.34%, underscoring its accuracy and reliability. This research significantly contributes to a deeper understanding and the qualitative enhancement of preparing high-quality syngas for SOC under improved process conditions. Enabling the early availability of valuable information drives forward sustainable research and ensures the safe, consistent operation assessment of r-SOC. Additionally, this strategic approach substantially reduces the need for resource-intensive experiments. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Figure 1

Review

Jump to: Research

46 pages, 26730 KB

Open AccessReview

AI-Driven Multi-Objective Optimization and Decision-Making for Urban Building Energy Retrofit: Advances, Challenges, and Systematic Review

by Rudai Shan, Xiaohan Jia, Xuehua Su, Qianhui Xu, Hao Ning and Jiuhong Zhang

Appl. Sci. 2025, 15(16), 8944; https://doi.org/10.3390/app15168944 - 13 Aug 2025

Cited by 3 | Viewed by 3746

Abstract

Urban building energy retrofit (UBER) is a critical strategy for advancing the low-carbon and climate-resilience transformation of cities. The integration of machine learning (ML), data-driven clustering, and multi-objective optimization (MOO) is a key aspect of artificial intelligence (AI) that is transforming the process of retrofit decision-making. This integration enables the development of scalable, cost-effective, and robust solutions on an urban scale. This systematic review synthesizes recent advances in AI-driven MOO frameworks for UBER, focusing on how state-of-the-art methods can help to identify and prioritize retrofit targets, balance energy, cost, and environmental objectives, and develop transparent, stakeholder-oriented decision-making processes. Key advances highlighted in this review include the following: (1) the application of ML-based surrogate models for efficient evaluation of retrofit design alternatives; (2) data-driven clustering and classification to identify high-impact interventions across complex urban fabrics; (3) MOO algorithms that support trade-off analysis under real-world constraints; and (4) the emerging integration of explainable AI (XAI) for enhanced transparency and stakeholder engagement in retrofit planning. Representative case studies demonstrate the practical impact of these approaches in optimizing envelope upgrades, active system retrofits, and prioritization schemes. Notwithstanding these advancements, considerable challenges persist, encompassing data heterogeneity, the transferability of models across disparate urban contexts, fragmented digital toolchains, and the paucity of real-world validation of AI-based solutions. The subsequent discussion encompasses prospective research directions, with particular emphasis on the potential of deep learning (DL), spatiotemporal forecasting, generative models, and digital twins to further advance scalable and adaptive urban retrofit. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) for Energy Systems)

► Show Figures

Journal Menu

Journal Browser

Artificial Intelligence (AI) for Energy Systems

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (6 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI