Search

Smart-grid optimization increasingly integrates digital twins, reinforcement learning, and cyber-physical resilience analytics into a shared research space. This convergence reflects a shift from isolated grid-control studies toward data-intensive, adaptive, and resilience-oriented infrastructure analytics. This bibliometric review maps the research landscape at the intersection of these three domains. It quantifies publication trends, identifies thematic clusters, and interprets emerging fronts in smart-grid optimization research. A structured bibliometric protocol was applied to 28 peer-reviewed journal articles published between 2017 and 2025. Co-word analysis, citation analysis, thematic clustering, and citation burst interpretation were used to organize the evidence base. The analysis reveals rising publication activity after 2019 and three dominant thematic clusters. Digital twin research centers on simulation and cyber-physical representation, reinforcement learning emphasizes adaptive grid control, and cyber-resilience analytics focuses on vulnerability, disruption, and recovery. The field is moving toward integrated frameworks that combine digital twins and reinforcement learning for proactive, cyber-resilient grid optimization. These fronts suggest a growing need for real-time, explainable, and safety-aware analytics.

Smart-meter data is sensitive, and its centralization raises privacy concerns. Federated learning and privacy-preserving techniques promise to enable analytics without compromising user confidentiality. The practical viability of these methods in real-world smart-grid applications remains uncertain. A critical synthesis of their limitations, privacy assumptions, and deployment gaps is still needed. This review critically evaluates the state-of-the-art in federated and privacy-preserving learning for smart-meter analytics, grid-edge control, and DER coordination. It focuses on both methodological promise and deployment realism. A critical review of 27 peer-reviewed articles from 2017 to 2025 is conducted. The assessment focuses on technical performance, privacy guarantees, scalability, security, and deployment readiness. The review identifies key strengths in theoretical privacy and decentralized learning. It also finds substantial limitations in communication efficiency, non-IID robustness, adversarial resilience, and energy-sector-specific feasibility. Federated and privacy-preserving learning holds great promise, but critical technical and regulatory barriers must be overcome. The review provides a roadmap for future interdisciplinary research.

Artificial intelligence is increasingly used for real-time decision support and control in cyber-physical smart grids. However, the growing reliance on data-driven control creates a need for methods that are both explainable to human operators and consistent with electrical-network physics. This review proposes a two-dimensional classification scheme for AI methods in smart-grid control. The scheme combines an explainability dimension with a physics-informed dimension and applies the resulting framework to voltage regulation, congestion management, and microgrid control. A systematic literature search identified 25 peer-reviewed journal articles published between 2017 and 2025. The selected studies were classified according to their explainability mechanism, degree of physical-knowledge integration, application domain, and relevance to cyber-physical grid operation. The review shows that most studies emphasize either explainability or physical consistency, while methods combining both remain limited. Voltage regulation is dominated by reinforcement-learning and safety-constrained control studies, whereas microgrid control contains a broader variety of AI methods. The proposed classification provides a structured basis for analysing trustworthy AI in smart-grid control. It highlights methodological gaps and identifies under-developed combinations of explainability, physics-informed learning, and operational deployment.

Real-time coordination of distributed energy resources is increasingly complex because distribution grids now operate with high variability, bidirectional power flows, and rapidly changing local constraints. Digital twins, graph neural networks, state estimation, and uncertainty-aware dispatch provide complementary capabilities for managing this complexity. This article proposes a layered digital-twin architecture that combines state estimation, graph neural network analytics, and uncertainty-aware dispatch for real-time DER coordination. The objective is to describe an architecture that is conceptual, modular, and suitable for active distribution network operation. The architecture is designed conceptually, with layers for physical grid mirroring, measurement fusion, topology-aware learning, and robust dispatch. A validation strategy is positioned as a future pathway rather than as an experimental contribution. The proposed architecture modularizes the DER coordination task into interoperable layers with distinct responsibilities and interfaces. Three tables are used to define the architecture layers, applicable GNN functions, and uncertainty-handling mechanisms. The architecture provides a blueprint for next-generation distribution management systems that require real-time observability, learning-based analytics, and robust decision support. It is intended to guide future implementation, simulation, and field validation.

High penetration of rooftop photovoltaic generation introduces rapid voltage fluctuations in low-voltage distribution feeders. These fluctuations challenge conventional voltage regulation because inverter actions must respond locally while remaining coordinated across electrically coupled nodes. This article proposes a multi-agent reinforcement learning model for grid-edge voltage regulation under distributed PV variability and communication latency. The objective is to maintain feeder voltages within operational limits while reducing unnecessary reactive power support, curtailment, and communication burden. The voltage control task is formulated as a decentralized partially observable Markov decision process. Smart inverter and battery agents use local observations during execution, while centralized training uses feeder-wide voltage, PV, and control information to train coordinated policies. Simulation results show that the proposed MARL controller improves voltage compliance relative to local Volt/VAr control and approaches centralized optimal power flow performance. The controller remains stable under bounded latency and asynchronous agent updates. The proposed framework offers a robust decentralized control strategy for high-PV distribution feeders. It combines grid-edge autonomy with coordinated learning, making it suitable for communication-limited voltage regulation.

Smart-meter load forecasting is essential for distribution-grid operation, flexibility scheduling, congestion management, and renewable integration. However, centralizing household-level smart-meter records can expose private behavioral patterns and reduce consumer trust. This article proposes a federated forecasting framework for accurate smart-meter load prediction across heterogeneous distribution feeders. The framework enables multiple feeders to collaboratively train forecasting models without transferring raw household consumption data. The proposed framework combines feeder-local temporal neural networks, federated aggregation, feeder-aware personalization, and optional differential privacy. It is validated through simulation on multi-feeder smart-meter datasets with different customer mixes, photovoltaic penetration levels, missing-data rates, and load variability. The framework achieves forecasting accuracy close to a centralized privacy-free benchmark while outperforming local-only and non-personalized federated baselines under strong feeder heterogeneity. Differential privacy introduces a controlled accuracy penalty that remains acceptable for day-ahead and intra-day feeder operation. The proposed federated forecasting framework provides a practical privacy-preserving solution for distribution system operators that need accurate load forecasts across diverse feeders. The results indicate that collaborative learning can preserve household privacy while improving feeder-level prediction accuracy.

Distribution-grid congestion is becoming more difficult to anticipate as photovoltaic generation, batteries, electric vehicles, and flexible demand reshape feeder power flows. Graph neural networks provide a natural way to represent feeders, but a conceptual framework is needed to connect topology, physics, and flexibility signals coherently. This conceptual research article proposes a physics-informed graph neural network framework for forecasting distribution-line congestion and voltage violations. The framework is designed to produce hourly congestion probabilities over a 24-hour horizon. The proposed model represents buses as graph nodes and lines or transformers as graph edges, while DER flexibility signals are encoded as forward-looking node attributes. Physical consistency is introduced through power-flow residuals, voltage-bound penalties, and thermal-limit penalties in the learning objective. Rather than reporting experimental results, the article specifies the architecture, input requirements, loss formulation, benchmarking logic, and explainability design required for future empirical validation. The framework is intended to guide implementation on realistic feeder datasets. The proposed PINN-GNN is expected to improve congestion awareness by combining electrical topology, flexibility availability, and physics-informed regularization. Its explainability layer is designed to help operators identify which lines, buses, or DER resources most influence a forecasted congestion event.

Cyber-physical attacks on smart grids can compromise the measurements, forecasts, and control signals used in dispatch. A resilient decision-support system must detect anomalies, explain their operational meaning, and support secure re-dispatch before manipulated data causes unsafe operation. This article proposes a cyber-resilient decision-support system that integrates anomaly detection, explainable alerts, and robust optimization for smart-grid dispatch. The system is designed as an operator-facing architecture rather than a standalone detection model. The system combines machine learning-based anomaly detection, explainable artificial intelligence-driven alert generation, and robust dispatch re-optimization. Validation is structured around false data injection, voltage measurement manipulation, and load manipulation attacks on an IEEE test feeder. The proposed decision-support system identifies cyber-physical anomalies, converts model outputs into actionable explanations, and updates dispatch decisions under attack-induced uncertainty. Compared with non-resilient dispatch and detection-only benchmarks, it reduces unsafe voltage excursions and avoidable line-flow stress. The integrated architecture improves cyber-resilience by connecting detection, explanation, and mitigation in one operational workflow. It supports faster operator interpretation while maintaining dispatch feasibility under uncertain measurements.

Autonomous control is increasingly relevant to smart-grid operation, where control systems may support voltage regulation, frequency control, dispatch, and anomaly response. Yet their trustworthiness remains uncertain when decisions are opaque, intervention options are unclear, and cyber-physical conditions are unstable. Existing research often treats explainability, operator intervention, and cyber-physical uncertainty as separate design or evaluation issues. This separation limits theory development because trust in autonomous grid control depends on how these mechanisms operate together. This article develops a conceptual theory of trustworthy autonomous smart-grid control. The theory links explainability, operator intervention, and cyber-physical uncertainty to both perceived and operational trustworthiness. The article uses theory-building logic rather than empirical testing. It synthesizes concepts from trustworthy AI, human-automation interaction, explainable AI, and cyber-physical security to construct mechanisms and derive propositions. The proposed model specifies causal pathways through which explanation quality, intervention capability, and uncertainty handling shape trustworthiness. It also identifies interaction effects, boundary conditions, and testable propositions for future research. The theory provides a foundation for designing, evaluating, and empirically testing trustworthy autonomous control systems in smart-grid environments. It emphasizes that trustworthiness is not produced by transparency, human oversight, or robustness alone, but by their coordinated operation.

Microgrids are increasingly relied upon to maintain supply during disruptions, but their resilience depends on timely islanding, accurate renewable forecasts, and efficient battery dispatch. Digital twins offer a platform to integrate these functions into a coordinated control environment. Existing microgrid control architectures often treat islanding, forecast uncertainty, and battery recovery as separate problems. An integrated conceptual framework that unifies them within a digital-twin environment is therefore needed. This article proposes a conceptual framework for digital-twin-assisted microgrid control that coordinates resilience-oriented islanding, renewable forecast error handling, and battery dispatch recovery. The framework is intended as a design-oriented contribution rather than an experimental validation. The framework is developed through conceptual synthesis of digital twin architectures, microgrid resilience theory, forecasting uncertainty modeling, and battery storage control. No experiments, simulations, field measurements, or empirical results are reported. The framework describes a multi-layered control architecture that continuously assesses resilience, triggers islanding under forecast uncertainty, and manages battery dispatch for post-islanding recovery. Four tables summarize digital twin functions, forecast error types, control architecture, and resilience indicators. The framework provides a design blueprint for resilient microgrid controllers that leverage digital twins. It can guide future simulation studies, hardware-in-the-loop testing, and field validations.

Reinforcement learning can autonomously dispatch demand response actions under changing prices, loads, and grid constraints. However, operator acceptance requires explanations that clarify why specific customers or aggregations are selected. This article presents an explainable reinforcement learning framework for demand response dispatch using customer flexibility profiles, decomposed rewards, and operator review. The objective is to preserve dispatch performance while improving transparency and controllability. The framework combines a profile-aware RL dispatcher, a decomposed reward model, an explanation generator, and a structured operator review protocol. Evaluation is performed through simulation on realistic demand response scenarios with household and flexible-load representations. The proposed explainable RL framework is designed to achieve dispatch performance comparable to black-box RL while providing interpretable action rationales. Operator review is incorporated to approve, reject, or modify dispatch recommendations before execution. The framework bridges autonomous RL control and trustworthy grid-edge operation. It provides an algorithmic blueprint for human-centered demand response dispatch.

Electric vehicle charging imposes new operational stress on distribution grids, especially where local transformer capacity and feeder voltage margins are limited. Grid-edge intelligence could enable charging decisions to be made closer to the physical constraints that shape those impacts. Existing EV charging control architectures often depend on centralized optimization, cloud-side visibility, or stable communication paths. Such designs can create privacy, latency, and resilience gaps when local operating conditions change rapidly. This article proposes a layered grid-edge intelligence architecture for distributed EV charging control. The architecture integrates local forecasting, federated model updates, and resilience-aware coordination into a unified system design. The architecture is developed conceptually through functional layers, interfaces, data flows, and operational workflows. Implementation scenarios and validation stages are outlined to guide future simulation, hardware-in-the-loop testing, and field deployment. The proposed architecture defines local forecasting nodes, a federated update layer, and resilience coordination functions that interact through structured protocols. Five tables are specified across the full manuscript to summarize model roles, coordination strategies, resilience mechanisms, deployment scenarios, and validation procedures. The architecture offers a blueprint for grid-edge EV charging management that balances intelligence, privacy, and resilience. It is intended to support future practical implementation rather than report experimental results.

The rapid expansion of electric vehicle (EV) adoption has led to a swift growth in charging infrastructure, accompanied by a rising incidence of malfunctions in charging equipment. To enhance the management and maintenance of these facilities, this study introduces an approach using the XGBoost algorithm, specifically tailored for direct current (DC) EV charging stations. A comprehensive operation and maintenance framework is developed, grounded in thorough condition evaluation. This framework incorporates the current functional state of the stations alongside patterns in user charging behavior. Key considerations include drivers’ traveling and recharging preferences, prevailing road congestion levels, and the condition of charging hardware. The model is trained on a dataset compiled from records, live surveillance information, and ambient external conditions. Employing the XGBoost technique, a robust evaluation model assesses the operational health of charging stations. Drawing from these evaluation outcomes and integrating relevant fault-related metrics, a dedicated risk evaluation framework is formulated. By using the energy not charged (ENC) metric, the system performs ongoing risk monitoring for each facility, assigns risk-priority rankings, and establishes a sequence for necessary interventions. An advanced optimization model for DC station maintenance is then constructed, balancing financial efficiency with system reliability objectives, ultimately generating an effective maintenance schedule across stations. Case study findings indicate that this combined condition assessment and strategic maintenance plan markedly enhances overall system dependability and delivers superior economic returns from upkeep efforts, all while satisfying established performance criteria.

Amid worsening worldwide environmental degradation and escalating carbon outputs from the construction sector, school campuses—serving as the main settings for young people’s education and daily life—hold significant importance in promoting designs that prioritize low-carbon approaches, enhanced energy conservation, and eco-friendly surroundings. This study examines the renovation of Yezhai Middle School in Qianshan, Anhui Province, as a specific example, investigating methods to improve airflow patterns and to implement facade-based energy conservation measures for hilly-terrain school facilities during upgrades to pre-existing structures. Within the broader push toward intelligent urban systems, embedding cutting-edge tools and eco-conscious methods into communal facilities has emerged as a central priority. By conducting airflow modeling and upgrading building exteriors for greater efficiency, the analysis demonstrates nonlinear increases in airflow velocity with increasing elevation, alongside notable influences of surface texture on fluctuations in wind conditions. Incorporating expanded polystyrene (EPS) boards, along with added thermal barriers, during exterior upgrades reduces heating demand in colder months and air conditioning demand in warmer months. The updated exteriors successfully block chilly drafts while minimizing unwanted solar heat absorption, resulting in energy savings of roughly 24%. These findings offer valuable technical guidance and real-world insights for implementing low-carbon, efficiency-focused upgrades across additional educational and civic structures, supporting the building sector’s shift toward sustainable, lower-emission practices within intelligent urban frameworks.

This research investigates how perceptions of Thai government policies affect the willingness to adopt electric vehicles (EVs). Shifting toward EVs plays a key role in cutting greenhouse gas emissions and addressing climate change, in line with international sustainability targets. The study fills important gaps by examining the various dimensions of how people view government policies and their effects on EV adoption intentions within emerging economies, with a specific focus on Thailand. Data were collected through a survey of 3,770 participants nationwide from January to March 2024. The questionnaire evaluated several aspects of government policy perceptions, such as commitment and implementation efficiency, social welfare considerations, communication efforts, overall policy effectiveness, and tax-related advantages. The analysis applied techniques including Exploratory Factor Analysis (EFA), second-order confirmatory factor analysis (CFA), and structural equation modeling (SEM) to confirm the measurement constructs related to perceived government support and to test their impact on intentions to purchase or use EVs. Results indicate that concrete government actions—especially those that expand EV charging infrastructure and establish transparent regulatory frameworks—alongside clear, effective policy communication strongly shape public readiness to embrace EVs. The study also underscores the vital influence of perceived governmental dedication and financial incentives on consumer choices. Drawing on these conclusions, the research suggests that policymakers should focus on rapidly scaling up charging networks, making the government’s resolve more visible to the public, and strengthening direct monetary support to accelerate EV uptake. These insights enrich the literature on EV adoption dynamics in developing countries and provide actionable guidance for authorities aiming to advance eco-friendly transport systems.

This research outlines a structured framework comprising 7 primary categories and 50 underlying sub-factors designed to evaluate the rollout of electric vehicles (EVs). To establish the local importance weights for these sub-factors, the study employed two approaches: variants of the Average Rank Transformation and the Analytic Hierarchy Process (AHP). Consensus among the specialists was achieved by averaging the rankings assigned to both the main categories and the sub-factors, thereby resolving the assessment task. The mean local weights were further derived using three distinct Multiple Criteria Decision-Making (MCDM) techniques, thereby enhancing the overall reliability of the outcomes. Consequently, the overall (global) weights and ranking order of the sub-factors were determined. According to the specialists, the nationwide advancement of EVs is predominantly influenced by the elevated expenses associated with producing and acquiring EVs, the provision of monetary subsidies to buyers of EVs, the elimination of tailpipe emissions, the rollout of rapid charging facilities, and the current shortage of supporting infrastructure across the nation’s five major urban centers. The analysis indicates that, among the 50 sub-factors, the top 10 most influential ones (predominantly tied to economic considerations) collectively account for over 35% of the total global weight. Meanwhile, the 22 highest-priority sub-factors exceed the mean weight threshold (0.2) and together represent roughly 65%. These insights offer practical guidance for government officials responsible for shaping EV adoption strategies.

To effectively respond to ongoing global shifts—including globalization, climate change, and population expansion—contemporary urban areas need to integrate digital technologies into their governance and operations. This study explores a framework for urban digitalization, drawing inspiration from the digital twin initiative implemented in Rotterdam. It outlines data-handling approaches suitable for diverse data origins. The discussion also covers associated cybersecurity vulnerabilities and the possible exploitation of smart city infrastructure for military purposes. Finally, by examining publicly accessible datasets on air quality monitoring and electricity use in public lighting, the study compares the functional capabilities of Rotterdam’s digital twin with those of the digital platform developed for Brno. The analysis reveals that each municipality adopts a distinct digital transformation strategy, making a standardized, universal model impractical. Consequently, urban digitalization remains highly context-specific and individualized. At present, both platforms primarily enable the visualization of aggregated urban data. However, neither has yet incorporated sophisticated capabilities, such as artificial intelligence-supported decision-making or predictive modeling of urban phenomena. Nevertheless, they generate valuable datasets that hold significant potential for external stakeholders and third-party applications.

The field of smart homes stands out as one of the most dynamic domains in advancing information and communication technologies. To deliver enhanced safety, user convenience, and efficient resource use, a smart home should be regarded as an advanced technological setup that integrates automation innovations with up-to-date building practices. Such systems can be incorporated into both newly constructed structures and the upgrading of older ones. This research explores the core concept of a smart home system, justifies the adoption of resource-efficient approaches and solutions, and assesses how these can be combined with the renovation of low-rise housing. The work presents a conceptual design of a smart home configuration tailored to a specific renovation case, along with a mobile-based interface for system management.

Cities undoubtedly play a crucial part in efforts to mitigate climate change. Many urban areas worldwide have pledged to pursue sustainability shifts by adopting environmentally friendly approaches. In recent years, Europe has seen a notable increase in smart city initiatives and progress toward building more sustainable urban environments. Currently, the idea of Positive Energy Districts (PEDs) is motivating districts and municipalities to move away from conventional practices and strive for greater carbon neutrality. This article examines five municipalities—Maia, Reykjavik, Kifissia, Kladno, and Lviv—that are participating in an active Horizon 2020 initiative. The main goal is to explore how these cities identified and chose the 10 solutions they plan to replicate. Data were gathered via conversations, interviews, and the replication roadmaps prepared by each city. It should be emphasized that every city faces unique conditions regarding political backing, funding availability, technical capabilities, and stakeholder engagement—circumstances that apply universally when introducing innovative, efficient measures. Municipalities throughout Europe and other regions may encounter comparable challenges, so this article also presents the experiences of these five Fellow Cities as they advance toward PED implementation.

Accurate short-term forecasting of household electricity consumption is vital to contemporary distributed energy networks. Most approaches to load prediction rely on deep neural architectures and require access to confidential, user-specific consumption records during training. Traditional neural network training typically collects all available data at a single central location to develop one unified model. Nevertheless, pooling individual user information in this manner raises serious concerns regarding data security and personal privacy. To address these issues, the present research explores federated learning techniques combined with model personalization as promising alternatives. Through a comprehensive simulation-based evaluation, these approaches are benchmarked against the standard centralized training strategy and a simple pre-trained reference model. The analysis reveals that the intrinsic characteristics and heterogeneity of the underlying electricity consumption patterns significantly affect the resulting model error levels. Consequently, directly contrasting error distributions across methods largely reflects differences in data composition rather than true differences in algorithmic effectiveness. To overcome this limitation, the study introduces a novel evaluation technique termed “differential comparison.” This approach focuses exclusively on pairwise loss differences across identical data instances, thereby enabling a fairer assessment of relative model improvements via the resulting difference distributions. Applying this method demonstrates that personalized model training outperforms all other strategies examined for residential load prediction, achieving better results in 59.1% of the evaluated scenarios.

Photovoltaic systems contribute substantially to electrical grid capacity, yet the intermittent nature of solar resources and uncertainties in output make grid balancing and reserve allocation challenging. Accurately forecasting solar production begins with reliably estimating clear-sky irradiance levels. While broadband atmospheric turbidity parameters can capture reductions in clear-sky conditions, the precision of these models hinges on data capturing current and future aerosol concentrations and water vapor levels. Obtaining such information requires observations that are both temporally and spatially proximate, given the high variability in turbidity. Unfortunately, these kinds of measurements are available in near real time only at a small—and shrinking—set of locations. This study introduces an innovative approach to infer time-dependent, site-specific turbidity levels using more widely accessible data from pyranometers or monitored PV system outputs. The technique leverages a long short-term memory (LSTM) recurrent neural network to isolate the turbidity-related component embedded within global irradiance (or PV power-derived) records, overcoming the natural suppression of this signal. Designed for near real-time implementation, the method supports solar forecasting needs. Evaluation focuses on two aspects: (1) its capacity to replicate turbidity values calculated historically from beam irradiance observations during clear-sky periods; and (2) its effectiveness when supplying turbidity estimates (via persistence forecasts based on daily averages) as inputs to clear-sky models.

Sophisticated machine learning (ML) techniques have demonstrated superior performance over conventional methods across numerous forecasting tasks, particularly in electricity price forecasting (EPF). Nevertheless, the predictive capability of these ML models deteriorates markedly when encountering input data that differs significantly from the examples observed during training. This phenomenon frequently occurs in EPF due to shifts in market conditions, such as surges in fuel costs, higher integration of renewable energy sources, or modifications in regulatory frameworks and operational rules. While the decline in accuracy on unfamiliar data is problematic, an even greater difficulty lies in the inability to anticipate when the model will produce unreliable outputs. This lack of foresight exposes electricity market participants—including bidding agents and retailers—to considerable financial risks stemming from erroneous price predictions. Consequently, it is critical to determine whether a given model prediction can be relied upon in real time. To address this need, the present study introduces a trust evaluation algorithm for EPF applications grounded in explainable artificial intelligence (XAI) methods. The proposed algorithm computes trust scores that indicate the reliability of each new prediction generated by the model. These scores are constructed in two phases: first, a preliminary score is derived from the correlation between local and global explanations; second, the score is refined using SHapley Additive exPlanations (SHAP) values for individual features. Such score-based interpretations are more accessible and actionable for EPF practitioners, such as asset managers and traders, than conventional feature-based visualizations. The effectiveness of the algorithm is assessed using datasets from the Italian electricity market and the Electric Reliability Council of Texas (ERCOT). Empirical results reveal that the method achieves over 85% accuracy in recognizing reliable predictions when the incoming data distribution closely matches the training distribution. Under conditions of distributional shift, the algorithm maintains a comparable level of accuracy in correctly flagging unreliable predictions.

Improving energy efficiency in the petrochemical sector is vital for reducing energy use and mitigating environmental harm. A reliable model for energy efficiency can provide important guidance for decision-making on operational process adjustments. In real-world settings, however, the varying sampling frequencies common in petrochemical facilities make conventional methods for estimating energy efficiency less dependable and more challenging to apply to multirate datasets. To address this, the present study introduces a multi-channel convolutional neural network framework that leverages transfer learning of model parameters to enhance energy efficiency forecasting despite irregular sampling rates. The multi-channel design enables the extraction of distinct temporal patterns by applying convolutions across the time axis of the data. At the same time, transfer learning enables the model to adapt and capture novel input behaviors after initial training. The effectiveness of this approach for both predicting energy efficiency and evaluating potential savings was demonstrated through its implementation in a vinyl chloride monomer manufacturing scenario. Results indicate that the suggested model surpasses standard benchmark approaches and conventional CNN architectures in predictive precision and consistency, achieving an R² value of 0.97. Incorporating transfer learning helps maintain robust performance without major declines and improves the model’s flexibility for continuous, real-time energy monitoring. In addition, an analysis of energy discrepancies identified substantial conservation opportunities, resulting in an average annual reduction in energy use of 7.25% and a corresponding decrease of 5,709 tons in CO₂ emissions.

Recent advancements have sparked growing interest in exploiting collections of pre-trained models, known as model hubs, particularly within computer vision applications. In practice, this involves first identifying a suitable pre-trained source model and then tailoring it to the new target domain to bridge any mismatches. Despite this trend, investigations into optimal model choice and tailoring methods for renewable energy generation forecasts remain scarce. Specifically, prior research has not delved into varied selection or adaptation techniques tailored to different neural network structures. Furthermore, no existing analyses have systematically evaluated how the volume of available training data affects outcomes, nor have they incorporated seasonal variations into performance assessments. We bridge these research gaps through an initial in-depth study of model selection and adaptation within transfer learning frameworks for renewable power prediction. Inspired by cutting-edge advances in computer vision, the analysis draws on operational data from 667 wind farms and solar (photovoltaic) installations across six datasets. To generate robust error metrics, we simulate scenarios with varying volumes of training observations across seasons. Model selection is then appraised using both marginal likelihood estimates and resulting forecast inaccuracies under these constrained data regimes. In addition, four separate adaptation methodologies are rigorously compared. Building on and surpassing conventional approaches, we introduce Bayesian linear regression to model the output variable from deep features derived by a neural network backbone. This technique delivers superior results compared to standard baselines, even with only 7 days of local training data. It also shows that full network fine-tuning provides negligible gains unless at least 3 months of data are available. Beyond that, we demonstrate that aggregating predictions from multiple models into ensembles markedly improves the effectiveness of both selection and adaptation. Consequently, ensemble-based strategies achieve mean error levels with only 30 days of training data that would otherwise require a full year of observations. In the most representative datasets, this yields average errors of 9.8% for photovoltaic power and 14% for wind power, utilizing only seven days of site-specific training data.

The growing integration of Distributed Generation (DG) and Demand Response (DR) resources into electrical grids has highlighted the need for innovative solutions to coordinate Price-Responsive Devices (PRDs). These devices operate as autonomous entities seeking to adjust their usage schedules in response to current electricity prices to maximize their individual benefits. Here, we introduce an innovative technique grounded in the Dantzig-Wolfe (DW) Decomposition to coordinate these autonomous PRDs within a decentralized framework. By leveraging the inherent parallel structure of DW, we treat the independent optimization routines of the PRDs as separate subproblems. A central entity—typically the utility or system operator—gathers the consumption proposals (bids) from these devices, resolves the master problem in the DW structure, and generates an appropriate price signal in response. This method achieves rapid convergence because the numerous subproblems—potentially numbering in the millions across many PRDs—can be addressed in parallel. Moreover, drawing on DW principles, if the individual device subproblems remain convex, the process converges to the globally optimal solution (corresponding to a Nash Equilibrium) after a modest number of rounds. The effectiveness of this framework was tested through a case study involving 200 participating homes, each with two load categories: Electric Vehicles (EVs), representing shiftable/interruptible loads, and Electric Water Heaters (EWHs), serving as thermostatically controlled appliances (TCLs). Simulations revealed that convergence to the optimum leads to lower overall generation expenses and reduced consumer bills (calculated via marginal generation costs), alongside a substantial drop in the aggregate demand’s Peak-to-Average Ratio (PAR).

The increasing deployment of wind power plays a key role in addressing climate change. Nevertheless, the intermittent nature of wind generation often leads to curtailment, resulting in substantial financial losses for wind farm operators. Battery energy storage systems (BESS) can help alleviate curtailment by providing local backup power. However, dedicating storage primarily to this supporting function can greatly diminish its profitability in energy markets. Optimal BESS operation requires carefully balancing local curtailment mitigation with participation in market bidding, yet achieving this in practice remains difficult owing to the intricate coordination required and the uncertainty of both electricity prices and wind output. This study explores a combined bidding strategy for a co-located wind-plus-battery setup operating in the spot market and the Regulation Frequency Control Ancillary Service markets. We introduce an innovative deep reinforcement learning method that separates the overall market engagement into two interconnected Markov decision processes—one for each asset. This structure allows the BESS to capture surplus wind energy that would otherwise be curtailed while simultaneously participating in joint bidding across markets to optimize total operational income. Validation was performed using real-world wind farm data. The proposed coordinated bidding approach outperformed a conventional optimization-based reference case, delivering roughly 25% higher revenue and achieving 2.3 times greater reduction in wind curtailment. Findings demonstrate that participating jointly in multiple markets substantially enhances the economic viability of wind-battery installations relative to engaging in individual markets in isolation. Additional simulations indicate that charging the BESS with otherwise curtailed wind power yields further economic benefits. Effective deployment of the developed algorithm is expected to promote greater co-location of renewable generation and storage facilities, thereby realizing broader advantages for the power system.

Modern smart grids aim to deliver exceptional reliability and operational flexibility in power delivery. Contemporary electrical networks rely on synchronized wide-area monitoring tools, notably Phasor Measurement Units (PMUs), to supply instantaneous system status updates. These devices support prompt problem identification and corrective actions while ensuring uninterrupted grid operation. The surge in available measurement data has accelerated the adoption of machine learning techniques for tasks such as power system protection and state estimation. This work presents an intelligent fault detection and classification (FD&C) framework for transmission lines that employs an auto-encoder neural network architecture. The study evaluates and contrasts the capabilities of a Multi-Layer Extreme Learning Machine (ML-ELM) with those of a Stacked Auto-Encoder (SAE) neural network. These models are further benchmarked against established classifier approaches that rely on wavelet-based feature extraction, as well as against various other deep learning strategies. The proposed auto-encoder solutions attain perfect (100%) fault detection rates and achieve fault classification accuracies of 99.92% and 99.79%, all while demanding far less computation time during the testing phase. The ML-ELM variant stands out for its efficiency, maintaining excellent classification performance with both training and testing durations below 50 milliseconds. To reflect practical field conditions, the models were rigorously tested on datasets incorporating additive noise levels corresponding to signal-to-noise ratios (SNR) between 10 dB and 40 dB. Validation was performed using simulated data from the IEEE 39-bus benchmark system.

This study investigates the prediction of fine-grained electricity peak demand using coarser-resolution data. Specifically, it addresses whether sparse high-resolution monitoring can inform forecasts of future high-resolution peaks when detailed measurements are unavailable, a question of particular importance for network operators evaluating the replacement of costly monitoring systems with predictive models. We develop models capable of estimating half-hourly maxima and minima from one-minute interval electricity load data using inputs aggregated to 30-minute intervals. Our methodology combines generalized additive models (GAMs) and deep neural networks (DNNs), both widely applied in load forecasting. The analysis includes an in-depth assessment of input feature importance, focusing on load patterns, meteorological variables, and seasonal trends. The proposed approach achieved first place in a data competition organized by Western Power Distribution (WPD), a UK electricity distribution operator. Beyond the competition, we conduct an extended evaluation over an additional 11 months, confirming that our combined model significantly outperforms the benchmark in out-of-sample root mean squared error (RMSE), achieving a 57.4% reduction compared to the competition reference.

This paper presents a real-time preventive control approach utilizing deep reinforcement learning (DRL) to identify optimal control actions that maintain an adequate secure operating limit (SOL) in power systems. The SOL represents the boundary of the most stressed pre-contingency operating condition that the system can endure following a specified set of credible contingencies while satisfying predefined stability requirements. The proposed DRL technique employs a hybrid control framework that enables simultaneous management of both discrete and continuous control variables. Its effectiveness is assessed using a modified Nordic32 test system. Findings indicate that the DRL method rapidly acquires a robust control policy capable of securing sufficient SOL across various operating conditions. The approach is benchmarked against a rule-based lookup table method and a DRL variant restricted to discrete actions. Results demonstrate that the hybrid DRL controller consistently outperforms the alternatives across all evaluated test cases, highlighting the advantages of jointly optimizing discrete and continuous variables for greater flexibility and operational efficiency.

Advancements in technology, continuous innovation, and the emergence of the Industry 4.0 paradigm are driving Distribution System Operators toward increasingly competitive environments where flexible demand response mechanisms are essential. In many developing nations, however, the absence of standardized measurement frameworks across industrial process chains hinders the effective deployment of demand-side management models, leading to inefficiencies in data analysis and limiting the accurate assessment of large-scale consumers’ contributions to flexibility. To address this gap, the present study utilizes load profile data—specifically energy and power measurements obtained from utility meters—as input variables to generate disaggregated forecasts at 15-minute intervals across four defined time segments. The proposed approach is validated through performance metrics, with outcomes assessed using the Root Mean Square Error (RMSE) to quantify total methodological error. The framework integrates Machine Learning and Big Data techniques implemented in Python, employing Combinatorial Disaggregation Optimization alongside Factorial Hidden Markov Models to enhance prediction accuracy.