Search Results (162)

The reliability of electric vehicle fast-charging infrastructure is becoming increasingly critical as deployment accelerates and the number of unavailable charging points grows. This work presents an unsupervised anomaly detection framework aimed at supporting predictive maintenance in DC fast-charging stations. The approach uses real minute-resolution operational data from a real charging station, including active, reactive and apparent power, power factor, phase power measurements and charger-side power measurements. Three complementary anomaly detection models were designed to capture different abnormal operating conditions: deviations in consumption patterns, efficiency losses between charger and grid analyser measurements, and phase imbalance in three-phase operation. Local Outlier Factor and Isolation Forest algorithms were integrated into an automated monitoring pipeline. Since labelled fault data were not available, validation was based on controlled injection of synthetic anomalies into real test signals, including physically coherent power disturbances, sensor or communication inconsistencies, progressive efficiency degradation and phase imbalance events. The results show that the framework is effective for detecting anomaly families that produce clear or sustained deviations, while more subtle temporal behaviours remain more challenging. Overall, the proposed framework provides a practical condition monitoring and early-warning approach that can support predictive maintenance decisions in DC charging infrastructure, while further temporal modelling is required for explicit degradation forecasting. Full article

Industrial energy transition has moved from pilot deployment to system integration, where renewable supply must be assessed together with process fit, organisational maturity, and uncertainty. This study proposes a risk-aware assessment framework integrating ISO 50001 energy-management maturity, ISO 31000 risk-management logic, a digital-twin-ready operational architecture, scenario simulation, Conditional Value-at-Risk (CVaR), and multi-criteria decision analysis. The study does not report a live plant-level digital twin or empirical survey validation. Instead, it specifies a five-layer implementation architecture, uses a synthetic survey-like dataset solely to demonstrate parameter recovery, and applies 350 Monte Carlo replications to an industrial energy hub comprising photovoltaic and wind generation, battery storage, and optional Power-to-H₂-to-Power storage. The quantitative workflow is reported with explicit equations, input assumptions, random seed, CVaR estimator, TOPSIS weights, and weight-sensitivity analysis. Under the adopted assumptions, the PV–wind–battery configuration achieved the lowest mean cost and CVaR, whereas hydrogen storage substantially reduced curtailment but increased mean cost and tail risk without materially reducing grid purchases. These results are conditional on the stated model assumptions and should not be generalised as empirical evidence. The framework supports structured investment and operational assessment by linking technical performance, organisational readiness, and cost–risk–decarbonisation trade-offs. Full article

Institutional governance has traditionally been analyzed under the assumption that the space of potential violations is finite, enumerable, and progressively constrainable through rule refinement and calibrated enforcement. The rapid integration of large language models into strategic and documentary decision-making challenges this premise by transforming feasible deviation spaces from bounded sets into generative manifolds. This paper develops a formal simulation framework for examining institutional stability under algorithmically amplified strategic exploration. Regulatory rules are modeled as a constraint manifold characterized by effective dimensionality, while generative systems expand the behavioral strategy space through semantic recombination under detection and sanction constraints. Stability is defined through a minimum deterrence margin evaluated across the generatively reachable domain rather than only through historical violation catalogs. The study uses a 2014–2023 regulatory and violation corpus to initialize and calibrate the simulation and to conduct a limited historical hold-out check; the 250,000 LLM-generated scenarios are treated as synthetic stress-test proposals rather than observed violations. The computational specification reports the generator checkpoint, embedding model, decoding parameters, prompt templates, random seeds, filtering rules, and label partitions used in the simulation. The model introduces a dimensional dominance principle: systemic vulnerability may emerge in the simulation when the effective dimensionality of generative strategic search expands faster than the independent constraint dimensionality of the rule system. Under the reported baseline setting, the synthetic simulations show a pipeline-specific dimensional crossover, convergence limits in rule-consistency classification, and a nonlinear detection–sanction response surface. These outputs are interpreted as diagnostics of the stated computational pipeline, not as universal empirical laws about real institutions. The power-grid component is delimited accordingly: the paper does not simulate physical grid operation, power flow, dispatch, or relay-protection dynamics; it interprets the model at the documentary governance layer of power-grid enterprises, including procurement, construction supervision, maintenance records, dispatch-related documentation, customer-service reporting, and internal audit. The framework therefore provides a reproducible and cautiously delimited basis for analyzing text-mediated institutional resilience in the age of generative intelligence. Full article

Electric vehicle (EV) charging demand introduces significant variability in power systems, requiring forecasting approaches capable of representing both aggregated consumption trends and stochastic charging behaviors. While machine learning methods often provide strong predictive performance, they generally require large datasets and substantial computational resources. This paper proposes a stochastic framework based on compound Poisson and Cox processes to model EV charging demand using real charging station data collected at one-minute resolution. The proposed methodology jointly models charging-event arrivals, charging duration, and charging power through probabilistic distributions calibrated from historical observations. A compound homogeneous Poisson process (CHPP) and a double stochastic compound Poisson process (Cox process) are investigated and compared for the generation of synthetic EV charging profiles and short-term forecasting applications. The framework is validated using 1863 charging sessions recorded at a workplace charging infrastructure composed of 37 charging terminals. Monte Carlo simulations are performed to generate synthetic daily charging profiles and evaluate the capability of the models to reproduce key operational indicators, including daily energy consumption and peak grid power demand. The CHPP process achieves average forecasting errors up to 0.8% for daily energy and 6.2% for maximum grid power demand. The results show that Poisson-based stochastic models can generate diverse and realistic charging profiles while requiring only limited historical data and having low computational complexity. The proposed approach provides an interpretable and computationally efficient probabilistic framework for EV charging demand forecasting, synthetic profile generation, and power system operational studies. Stochastic compound Poisson processes may therefore constitute a valuable tool to support the ongoing electrification of mobility and the digital transformation of future smart grids and smart cities. Full article

To address the issues of neglecting population heterogeneity and the difficulties in determining constraint parameters in residential load adjustable capacity forecasting, this paper proposes a data-driven forecasting method that considers profile heterogeneity. First, K-means++ is utilized to extract diverse user electricity consumption profiles. Second, to solve the problem of real response data scarcity, the difference-in-differences (DID) method is employed to empirically calibrate the true physical constraint boundaries of different clusters, and high-quality response samples are generated in batches based on an electricity cost minimization model. Finally, a Long Short-Term Memory (LSTM) time-series forecasting model is constructed to achieve the precise quantitative evaluation of adjustable capacity. Case studies demonstrate that after introducing user profile labels, the three accuracy metrics of the predictive model are improved by 16.29%, 24.52%, and 20.21%, respectively. Although the practical application of synthetic labels faces minor limitations caused by uncertain user behaviors, this scalable framework supports seamless incremental retraining using future empirical response data to realize continuous model evolution and persistent accuracy improvement, thereby providing technical support for load aggregators’ market bidding and the precise dispatch of power grid demand response. Full article

Limited by the computational performance limits of the CPU(Central Processing Unit), the traditional Spark architecture struggles to achieve high throughput and low latency under the dual pressure of a large data scale and real-time requirements in centralized control systems. This work uses a publicly available CNC(Computer Numerical Control) milling dataset as a functional validation proxy for time-series data processing, then extends validation to a large-scale synthetic power transmission grid dataset. Furthermore, Spark-GPU(Graphics Processing Unit) collaboration suffers from load balancing failure due to heterogeneous resource scheduling and communication overhead, thus failing to unleash its performance potential. This paper proposes a Spark-GPU fusion acceleration technology path. The path consists of three key components: first, it integrates the RAPIDS accelerator; second, it designs a GPU-aware partitioning and task co-scheduling strategy; and third, it optimizes the zero-copy data path. Together, these components realize an integrated collaboration of heterogeneous resources. Validation on real-world datasets yields the following results. In real-time aggregation scenarios, the proposed solution improves throughput by a factor of 3.7 over the pure CPU baseline and reduces end-to-end latency by 62%. Compared with the basic GPU solution, GPU utilization rises from 51.7% to 72.3%, representing a relative improvement of 39.8%. Furthermore, the solution meets industrial-grade high availability requirements. This research significantly improves the processing throughput and reduces end-to-end latency in typical centralized control scenarios, thus providing a feasible technical route for demanding concurrent centralized control scenarios such as electric power industry manufacturing with high real-time demands. Full article

Non-Intrusive Load Monitoring (NILM) enables estimation of the energy use of individual appliances in smart buildings from a single aggregate meter. In practice, however, this task is not straightforward. Signals from different appliances can overlap, and the measured data may also include distortions such as spikes, drops, and noise. To address these issues, this study presents a multi-task triple-hybrid deep learning framework that handles appliance classification and anomaly detection together. The model brings together 1D-CNN, BiLSTM, and Transformer Attention so that local patterns, temporal dependencies, and wider contextual information can be learned within the same structure. It also uses a dual-output design to classify appliance categories and detect anomaly types simultaneously. Experiments were carried out on Building 1 of the UK-DALE dataset with four appliances: kettle, microwave, washer dryer, and fridge freezer. For the anomaly task, synthetic disturbances were added to segmented signal windows and grouped as normal, spike, drop, and noise. To check how well the proposed framework handled different scenarios, it was tested on both the UK-DALE and REDD datasets. Looking at the main UK-DALE results, the model correctly identified appliances 99.48% of the time and spotted anomalies with 98.80% accuracy. A secondary test on the REDD dataset yielded an 86.44% classification score. This proves the architecture can adjust to completely new power grid environments without losing its edge. On top of that, when pitted against standard benchmark models like Seq2Point, this triple-hybrid design clearly does a better job of mapping out complex signal changes. As a result, it yields much stronger anomaly detection metrics. Full article

Modern power systems are becoming increasingly complex due to the rapid integration of renewable energy sources, the widespread use of nonlinear power-electronic devices, and the deployment of microgrids operating in parallel with conventional power grids. These evolving conditions intensify the occurrence of diverse and highly complex power quality disturbances (PQDs), demanding accurate and computationally efficient monitoring strategies. This paper presents a novel multi-stage hierarchical framework for PQD detection and classification, comprising an initial training stage with a dedicated 1D Convolutional Neural Network (1D-CNN), a transfer learning stage, and a subsequent fine-tuning stage. The proposed approach operates directly on raw voltage waveforms, eliminating the need for any signal preprocessing, as the CNN performs internal feature extraction. The framework is evaluated using a comprehensive dataset that includes synthetic signals, Matlab/Simulink (version R2022a) time-domain simulations, and real voltage sag events. Additionally, up to 29 types of disturbances, including complex multi-event combinations defined by the IEEE-1159 Standard, are generated using the PQ-SyDa toolbox. The proposed model achieves an F1-score of 97.8% using a three-cycle analysis window and further improves to 98.86% when five cycles are used. These results highlight the robustness and generalization capability of the proposed approach for the real-time PQD monitoring task in modern electrical networks. Full article

Accurate short-term forecasting of residential electricity demand is increasingly important for smart distribution systems, particularly in the context of demand-side management and flexibility-oriented grid operation. In this study, a high-resolution forecasting framework is proposed in which household electricity demand is classified into fixed, shiftable, and adjustable load categories and forecasted together with total load. A one-minute-resolution synthetic residential load dataset is generated using the Centre for Renewable Energy Systems Technology (CREST) demand model for households with two to five occupants over a 31-day winter period in January. The appliance-level demand data are grouped according to operational characteristics and integrated into a representative four-bus distribution feeder. Minute-level power flow analysis is then performed to calculate technical losses, which are incorporated into the forecasting dataset together with meteorological variables (temperature, wind speed, and solar irradiance) and temporal descriptors. Using this multi-input structure, random forest (RF), support vector machine (SVM), feed-forward neural network (FFNN), and long short-term memory (LSTM) models are comparatively evaluated for the prediction of fixed, shiftable, adjustable, and total residential loads. Model performance is assessed using root mean square error (RMSE) and Pearson correlation coefficient (R), while mean absolute error (MAE) is additionally reported for the final test set. The results show that the LSTM model provided the most consistent overall forecasting performance, particularly for shiftable, adjustable, and total load estimation, while RF yielded competitive results for fixed-load correlation and short-window forecasting in Buses 1 and 2. In contrast, SVM and FFNN exhibited weaker generalization performance across several load categories. The proposed framework provides a practical foundation for the development of dynamic pricing mechanisms that consider load-type-based controllability levels. Overall, the findings demonstrate that integrating load categorization with meteorological, temporal, and technical loss information provides a robust and reproducible framework for smart grid applications such as demand-side management, peak load mitigation, and flexibility-aware residential load analysis. Full article

Anaerobic digestion is a viable pathway to mitigate environmental impacts from swine manure in tropical regions while contributing to circular economy strategies. However, no standardized or integrated framework currently exists that simultaneously quantifies the closure of energy, material, carbon, nutrient, and water loops at the farm scale. This research presents the techno-economic design and environmental assessment of a covered, mechanically agitated lagoon biodigester for a 10,000-head swine fattening module located in Matanzas, Cuba. The system is sized by integrating hydraulic, thermal, and structural parameters, and its economic viability is assessed through Net Present Value (NPV = $1.09 million), Internal Rate of Return (IRR = 32%), and a payback period of approximately three years. A comparative screening-level life cycle assessment shows that biogas-based electricity generation substantially reduces impacts on climate change, air quality, and fossil fuel scarcity compared with conventional diesel-based generation, with trade-offs in eutrophication and ecotoxicity. As a key methodological contribution, five quantitative circular economy indicators are proposed and calculated: the Energy Self-Sufficiency Ratio (ESSR = 1.71), the Waste Valorization Index (WVI = 0.91), the Decarbonization Index (DCI = 6.7), the Fertilizer Substitution Rate (FSR = 16.3 t N year⁻¹), and the Water Closure Factor (WCF = 1.30). These indicators show that the system achieves a 71% net energy surplus, valorizes over 90% of the input mass, avoids 6.7 times more emissions than it generates, replaces synthetic fertilizers, and returns more water than it consumes. The findings provide quantitative evidence that the convergence of mesophilic operation without auxiliary heating, high carbon intensity of the power grid, and availability of agricultural land enhances circularity performance in tropical covered lagoon bioreactors, and the proposed integrated indicator framework, aligned with ISO 59020:2024, provides a reproducible and transferable methodological basis for the comparative assessment of anaerobic digestion systems for livestock waste. Full article

Automated power line inspection plays a crucial role in maintaining grid reliability within smart cities by identifying potential defects in towers, conductors, insulators, and fittings. While modern anomaly detection relies heavily on deep neural networks (DNNs), training these models requires massive amounts of high-quality image data. However, a significant scarcity of publicly available datasets persists because data acquisition not only demands highly specialized professional skills but also faces strict data protection regulations enforced by grid companies. To bridge this gap, this paper presents a comprehensive review of open-access image datasets dedicated to power line inspection. Based on strict inclusion criteria—specifically, unrestricted public availability and a direct focus on core power line components—19 datasets are systematically selected and analyzed. We provide a detailed taxonomy and comparative analysis of these datasets in terms of inspection targets, acquisition platforms, annotation toolkits, and labeling schemes. Furthermore, our investigation highlights current research trends and identifies critical gaps, such as the disproportionate focus on insulators and the notable scarcity of multimodal data. To address the limitations of small-scale datasets, we also discuss existing data augmentation strategies and synthetic data generation techniques. Ultimately, this review serves as a unified navigational guide, aiming to foster the development of more robust visual inspection algorithms and to inspire future high-quality dataset construction in the power domain. Full article

The rapid proliferation of Large Language Models (LLMs) is increasing electricity demand from data centers, creating new challenges for power-demand forecasting and grid planning. A key difficulty is that architecture- and deployment-related information that affects inference load is often private to LLM providers. This paper proposes a two-stage, mechanism-assisted forecasting framework under information asymmetry. In the first stage, a stylized incentive mechanism elicits verifiable reduced-form demand parameters from LLM providers at a chosen reporting precision. In the second stage, the elicited parameters are incorporated into forecasting models as architecture- and deployment-informed features. Using calibrated synthetic scenarios constructed from public data-center energy reports, open LLM-inference energy benchmarks, and secondary public estimates, we find that incorporating elicited parameters reduces the mean squared error (MSE) of the ResNet forecasting backbone by 65.1% relative to an architecture-agnostic ResNet baseline. Similar improvements are observed for a gradient-boosting model, indicating that the main empirical value comes from procuring informative provider-side demand features rather than from a specific neural architecture. The results should be interpreted as a proof-of-concept demonstration rather than a full operational model of LLM serving or power-system dispatch. Full article

Multi-Agent Reinforcement Learning (MARL) provides an effective approach for urban multi-intersection traffic signal control. However, existing methods have faced two fundamental challenges, policy homogenization and inefficient credit assignment. The former led to convergent agent policies that failed to adapt to heterogeneous traffic patterns, while the latter prevented agents from accurately evaluating their individual contributions to system performance. To address these issues, this paper proposes a Multi-Agent Hierarchical Contrastive Learning Traffic Signal Control (MAHCL-TSC) model. The model incorporates an unsupervised contrastive learning module that enhances the discriminative power of state representations, thereby alleviating policy homogenization. Additionally, it designs a hierarchical graph convolutional credit allocation network that leverages road network topology and functional characteristics to enable structure-aware collaborative value estimation, significantly improving the precision of credit assignment. Based on these components, a Contrastive QTRAN with Hierarchical Graph Convolution (CQTRAN-HGC) algorithm is proposed, which jointly optimizes contrastive learning loss and QTRAN constraint loss. Experiments conducted in the Simulation of Urban Mobility (SUMO) simulation environment on 4 × 4 and 6 × 6 synthetic grid networks demonstrate that the proposed model improves traffic signal control performance under the tested structured simulation settings and shows potential scalability as the network size increases. Full article

Modern power systems are undergoing a structural transformation driven by the rapid integration of renewable energy sources, distributed energy resources, electrification, and increasing operational uncertainty. These developments expose the limitations of traditional centralized energy management and rule-based automation in highly distributed, data-intensive, and dynamically coupled energy infrastructures. In response, recent advances in artificial intelligence offer new opportunities for improving prediction, coordination, and adaptive control. This paper develops a reference architecture for Autonomous Energy Systems based on the integration of generative AI, agentic AI, digital twins, and distributed cyber–physical energy infrastructures. Rather than treating forecasting, control, simulation, and market coordination as separate research tracks, the paper organizes them within a common architectural perspective. Generative AI is positioned as a source of scenario intelligence, synthetic data generation, and uncertainty-aware forecasting, while agentic AI is framed as a bounded decision layer for perception, reasoning, planning, and coordinated action under operational constraints. The paper further clarifies the distinction between agentic AI, conventional multi-agent systems, and multi-agent reinforcement learning in energy applications. Representative application domains are discussed, including self-healing power grids, autonomous energy markets, and digital twin training environments. Major open challenges are identified in relation to scalability, physical consistency, safety verification, sim-to-real transfer, cybersecurity, interoperability with legacy infrastructures, and governance. The paper concludes by outlining a research agenda for the staged and safe development of increasingly autonomous energy systems. Full article

Due to the complexity of recent power grids, any fault can dramatically affect the system’s quality, reliability, and stability. As a result, identifying faults becomes essential to maintaining the stability and reliability of power systems within acceptable thresholds. This article presents an innovative binary classification fault detection method in recent power grids. The proposed methodology primarily consists of two preliminary stages before the training phase: data preparation and pre-training, aimed at improving the performance of the classifier. During the data preparation phase, the synthetic minority over-sampling approach balances the raw data, and the pre-training phase identifies the optimal features and hyperparameters. A novel hybrid approach combines the Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) methods to optimize feature selection and adjust hyperparameters. Furthermore, four machine learning models are trained and evaluated using an actual fault dataset. In addition, several evaluation criteria and receiver operating characteristic curves are used to validate the strength and robustness of the suggested method. All experimental evaluations were performed in an Azure Machine Learning Studio (AMLS) environment. The experimental results are compared to previous studies to verify the superiority of the suggested technique. Full article