Search Results (161)

AC/DC hybrid building microgrids require an energy management system (EMS) that coordinates distributed energy resources while maintaining fast local responses to communication and device faults. This study proposes a knowledge-graph-enhanced edge-cloud EMS for an AC/DC hybrid building microgrid. A 24 h linear-programming scheduler coordinates multi-resource dispatch in the cloud, while edge controllers enforce local safety constraints, correct setpoints and maintain fallback operation during link interruptions. The knowledge graph provides semantic context by linking assets, constraints, faults and admissible actions. Six operating scenarios, controlled V2G ablation tests and workday–weekend validation were used to assess the framework. Compared with rule-based EMS, the proposed method reduced peak demand by 28.0% and increased PV self-consumption from 78.4% to 95.4%. Compared with cloud-only MPC, it reduced the simulated mean control-loop latency from 7.54 s to 0.81 s. The eight-rule fault evaluation achieved a mean trigger accuracy of 94.6%. Under normal operation, however, the higher PV self-consumption was accompanied by a modest increase in operating cost and peak demand relative to non-KG edge-cloud MPC. These results support the complementary use of cloud scheduling, edge autonomy and semantic context within the tested simulation scope. Full article

Microgrids are emerging as a promising solution to enhance renewable energy integration, energy reliability, electricity access, and sustainability in Morocco. This paper reviews the development of sustainable microgrids in the Moroccan context by analyzing existing projects, system configurations, control approaches, and energy management strategies. In line with Morocco’s objective of reaching 52% renewable electricity capacity by 2030, the reviewed studies show that hybrid microgrids combining photovoltaic, wind, battery storage, diesel backup, and pumped hydro storage can improve energy autonomy, reduce dependence on fossil fuels, and support a more sustainable energy transition. Across the reviewed case studies, reported performance indicators include renewable energy penetration of up to 97%, a Loss of Power Supply Probability (LPSP) of 0.0489, Levelized Cost of Energy (LCOE) values ranging from 0.038 to 0.17 USD/kWh, and energy cost reductions of up to 20.7% in building-integrated photovoltaic applications. These values are study-specific and should be interpreted as indicative performance outcomes rather than directly comparable benchmarks, since they depend on system size, load profile, storage technology, tariff structure, and optimization assumptions. The review also highlights the role of advanced control and optimization techniques, such as particle swarm optimization, model predictive control, equilibrium optimizer, and adaptive energy management systems, in improving power balance, reliability, cost-effectiveness, and sustainability. Finally, this paper identifies the main technical, economic, regulatory, and institutional barriers limiting large-scale sustainable microgrid deployment in Morocco and proposes recommendations to support decentralized, resilient, and environmentally sustainable renewable energy systems. Full article

Vehicle-to-grid (V2G) integration in commercial building microgrids (CBMGs) offers a promising path for grid support, economic arbitrage, and resilience enhancement. However, practical implementation is hindered by the optimization–execution gap, where high-level aggregated commands fail to match low-level physical charger capacities and individual battery boundaries, as well as by the lack of sociotechnical coupling under extreme weather events, where vehicle owner range anxiety dominates. To address these challenges, a closed-loop multi-timescale energy management system for V2G-enabled CBMGs under exogenous meteorological conditions is proposed. The framework features an integrated four-layer cyber–physical control architecture connecting macroscopic day-ahead scheduling, receding-horizon model predictive control (MPC), discrete real-time parking slot allocation with hardware safety boundary constraints, and equipment-level power flow execution. To handle extreme events, an exogenous meteorological stress index is formulated to quantify ambient structural hazards and temperature deviations, which are then mapped to owner range anxiety and loss-aversion behaviors using prospect theory. Rather than relying on heuristic rule-switching, the optimizer executes a smooth and continuous transition from normal economic peak-shaving to active pre-disaster energy reservation and load demand survival. The cyber–physical system is validated using high-fidelity simulations under typical summer and winter blizzard scenarios. The results demonstrate that the proposed hierarchical architecture successfully eliminates optimization–execution mismatches and guarantees zero load shedding. Furthermore, sensitivity analyses establish the optimal system configuration with the critical defense tolerance of 0.6 and the baseline anxiety ratio of 4, which successfully resolves the trade-off between premature defensive actions and insufficient energy reserves while considering human behavioral uncertainty. Full article

Against the backdrop of accelerating transitions to sustainable energy systems, the optimal operation of microgrids and the high-efficiency integration of renewable energy face growing technical challenges, which highlight the necessity of tapping into flexible multi-energy resources to the fullest extent. Aiming at low-carbon microgrid systems with electro-thermal demands, this paper proposes a sustainable dispatch strategy that actively integrates waste heat recovery and building thermal inertia. First, a refined mathematical model of a Hybrid Energy Storage System (HESS) is developed, considering waste heat recovery processes from the electrolyzer and the fuel cell. Second, an optimal dispatch model considering the HESS and building thermal inertia (BTI) is constructed, the PMV index is adopted to quantify the adjustable margin of user thermal demand, and the objective function accounts for multiple economic and environmental indices, including energy procurement costs, equipment maintenance costs, and carbon emission trading costs. Case studies show that this strategy can effectively enhance the regulation flexibility of the system, significantly reducing comprehensive operational costs by up to 51.6% and improving local renewable energy accommodation while ensuring environmental sustainability and low-carbon operation. Full article

Industrial microgrids are emerging as important providers of demand-side flexibility for active distribution networks. However, their participation in source–load coordination is hindered by complex production constraints, limited dispatch executability, and the widespread reliance on baseline-based demand response mechanisms. To address these challenges, this paper proposes a baseline-free source–load coordination framework for industrial microgrid clusters. A linear state–task network (LSTN) model is employed to characterize industrial production processes while preserving equipment operation, material balance, buffer storage, and production target constraints. Based on the feasible operating regions of individual microgrids, a simplified optimal adjustable load model (OALM) is developed at the aggregator level to identify and aggregate cluster-level flexibility boundaries without disclosing detailed production information. Building upon the aggregated flexibility region, a baseline-free target power tracking strategy is established, in which the distribution network issues absolute power targets and the aggregator coordinates multiple industrial microgrids to achieve their realization. The proposed framework simultaneously ensures production feasibility, scalable flexibility aggregation, and practical dispatch implementation. Case studies demonstrate that the aggregated industrial load can accurately track dispatch targets while satisfying all production constraints, thereby enhancing the capability of industrial microgrid clusters to participate in large-scale source–load interaction and renewable energy accommodation. Case study results show that when the number of industrial microgrids increases from 10 to 200, the total computation time increases from 5.08 s to 337.40 s, while the target tracking error remains within numerical tolerance. Compared with the conventional baseline-based virtual-battery (VB) method, whose root mean square error (RMSE) with respect to the intended absolute target reaches 241.30 kW under a ±10% baseline estimation error, the proposed method achieves near-zero tracking error. In addition, the production-agnostic aggregation model expands the flexibility boundary by 21.84% and generates targets that are not exactly executable under the full LSTN production constraints. Full article

The extensive deployment of renewable energy sources (RES) across modern energy infrastructure has introduced significant operational complexity, necessitating the development of advanced data-driven control strategies to ensure reliable and efficient system operation. Among these approaches, reinforcement learning (RL) has emerged as a promising paradigm for managing renewable generation and coordinating interconnected energy subsystems under uncertainty and dynamic operating conditions. The current paper presents a comprehensive review of RL-based control applications across RES-integrated energy domains, including power grids, microgrids, and building energy systems. The paper begins by outlining the fundamental characteristics of these smart grid energy environments along with the mathematical foundations of RL and its principal algorithmic families. A structured analysis of recent peer-reviewed studies is then conducted, with the literature systematically categorized according to the corresponding energy domain. A high number of impactful selected studies are further examined across multiple key dimensions, including RL methodologies, agent architectures, reward design, baseline control strategies, RES-integrated technologies, and control objectives. Based on this multi-dimensional evaluation, the review identifies emerging trends and highlights dominant design patterns across power grid, microgrid, and building-level applications. Finally, the observations are critically discussed and future research directions are outlined towards the development of scalable, practical, and reliable RL-based energy management solutions for next-generation smart grid systems. Full article

Accurate power load forecasting is critical for the efficient operation of industrial microgrids. However, raw meteorological and consumption data typically exhibit non-stationary characteristics, complicating the hyperparameter tuning of deep learning models, and subsequently degrading the prediction accuracy of these frameworks. To address the aforementioned challenges, a new hierarchical forecasting structure denoted as INRBO-SSA-LSTM is proposed in this paper. First, Pearson correlation analysis is employed for feature reduction, identifying the four main factors to mitigate the dimensionality curse. Building upon this foundation, a refined Newton-Raphson-Based Optimizer (INRBO) is introduced, integrating a cosine adaptive t-distribution perturbation, a boundary-aware non-uniform steering scheme, and a fitness-aware hybrid perturbation mechanism. Evaluated against the CEC2022 benchmark suite, comprehensive evaluations reveal that the INRBO demonstrates superior global exploration and local refinement capabilities compared to baseline algorithms when assessed on the CEC2022 benchmark suite for foundational optimization performance. Furthermore, rigorous testing on the CEC2017 suite across 10, 30, and 50 dimensions successfully validates its exceptional robustness and search capabilities in high-dimensional spaces. INRBO functions as a dual-stage optimizer within the proposed framework; in the initial phase, it dynamically calibrates the parameters of Singular Spectrum Analysis (SSA) to extract deterministic load patterns, achieving a maximum signal-to-noise ratio of 15.87 dB; in the second phase, it optimizes the global hyperparameters of the Long Short-Term Memory (LSTM) network. Validated using actual industrial microgrid data in Jiangsu Province, China, the proposed method significantly outperforms traditional baseline models across all indicators; specifically, the prediction error (RMSE = 10.9764, MAPE = 3.7866%) is substantially minimized, and the coefficient of determination ($R^2$ = 0.9741) is highly optimal. This adaptable framework effectively accommodates temporal demand variations, offering a robust foundation for the advancement of intelligent power management technology. Full article

Shipboard DC microgrids face critical stability challenges including low-inertia-induced voltage fluctuations and impedance mismatch caused by constant power loads (CPLs), which severely threaten system stability. Existing virtual DC machine (VDCM) control methods typically treat inertia support and impedance optimization as separate design objectives, lacking a unified frequency-domain design framework. To address this issue, this paper first establishes an accurate virtual impedance model for the standard VDCM controller, quantitatively revealing how its control parameters (J and D) shape the frequency-domain impedance characteristics and identifying potential stability conflicts. Building upon this model, a feedforward-compensated VDCM (FFC-VDCM) strategy is proposed, introducing a differential feedforward loop to actively reshape the converter output impedance in the critical mid-frequency range without interfering with the inertia support function. The impedance reshaping effect is quantified via impedance-based stability analysis; the proposed method improves the gain margin from $4.1$ dB (with conventional VDCM) to $8.6$ dB, along with a significant enhancement in the phase margin, confirming improved system robustness. Hardware-in-the-loop (HIL) experiments conducted under realistic shipboard conditions further confirm the theoretical analysis, demonstrating superior transient voltage regulation and validating the practical effectiveness of the proposed strategy. The FFC-VDCM provides a synergistic solution for concurrently improving inertia and stability in low-inertia DC microgrids. Full article

African universities face persistent energy insecurity that disrupts teaching, research, and campus operations. While renewable energy adoption is growing, hydrogen-based hybrid renewable energy systems (HRES) remain underexplored, and standard evaluation tools are lacking. This paper presents a replicable techno-economic framework for integrating renewable-hydrogen systems into university microgrids using Hybrid Optimization Model for Multiple Energy Resources (HOMER) simulation. The framework evaluates reliability, environmental impact, economic feasibility, and scalability under real campus conditions. A case study of the Mangosuthu University of Technology (MUT) Engineering Building compares three scenarios: grid-plus-diesel backup, (photovoltaic) PV–battery–hydrogen hybrid with grid support, and PV–battery–hydrogen hybrid with diesel backup. Results indicate that the PV–battery–hydrogen configuration with grid support achieved 98% reliability, a 74% reduction in Carbon dioxide (CO₂) emissions, and an Levelized Cost of Energy (LCOE) of $0.124/kWh, outperforming the current grid–diesel setup. These findings confirm the framework’s effectiveness as a benchmarking tool and its potential to guide African universities toward resilient, low-carbon energy systems aligned with national transition goals. Full article

Driven by the global energy transition and carbon neutrality goals, hybrid power systems have become a core technical path for energy conservation and carbon reduction in the transportation and power sectors, and the performance of energy management strategies directly determines the system’s overall energy efficiency. Traditional energy management methods have inherent bottlenecks of high model dependence and poor adaptability, making it difficult to satisfy real-time decision-making requirements under complex operating conditions. Deep Reinforcement Learning (DRL) provides an innovative solution to this technical bottleneck, and has become a cutting-edge research direction in this field. However, existing reviews have not yet constructed a full-chain analysis framework covering its algorithms, applications, verification, challenges and prospects. Focusing on the engineering application of DRL in the real-time energy management of hybrid power systems, this paper systematically sorts out domestic and international research results up to the first quarter of 2026. The core quantitative findings of this review are as follows: (1) DRL-based strategies can achieve 93–99.5% of the Dynamic Programming (DP) theoretical global optimum in fuel economy, which is 5–25% higher than rule-based methods; (2) DRL strategies only have 3.1–4.8% performance degradation under unseen operating conditions, which is significantly better than the 10.3–14.7% degradation of the Equivalent Consumption Minimization Strategy (ECMS); (3) Actor–Critic (AC) algorithms (Twin Delayed Deep Deterministic Policy Gradient (TD3)/Soft Actor–Critic (SAC)) have become the mainstream in this field, with a 3–5 times higher sample efficiency than value function-based algorithms; and (4) offline DRL and transfer learning can reduce the training time of DRL strategies by more than 80% while maintaining equivalent optimization performance. This paper first analyzes the essential attributes and core technical challenges of hybrid power system energy management; second, classifies DRL algorithms from the perspective of control engineering and analyzes their technical characteristics; third, disassembles the application design logic of DRL around four major scenarios: land vehicles, water vessels, aerial vehicles and fixed microgrids; fourth, summarizes the mainstream verification platforms and evaluation systems; fifth, analyzes core bottlenecks and cutting-edge solutions; and finally, prospects the development trends of next-generation intelligent energy management systems combined with cross-fusion technologies. This paper aims to build a complete technical system map for this field and promote the engineering deployment and practical application of intelligent energy management technologies integrating data and knowledge. Full article

As the global response to climate change and energy crises accelerates, the large-scale integration of heterogeneous distributed energy resources (DERs) is rapidly transforming traditional passive distribution networks into active distribution networks. However, the massive quantity and high stochasticity of these underlying devices trigger a severe “curse of dimensionality,” creating significant computational and communication bottlenecks for coordinated system dispatch. To overcome these challenges, the “clustering followed by equivalence” aggregation modeling paradigm has emerged as a critical technical pathway. This paper reviews the state-of-the-art clustering and aggregation methodologies for distribution networks with high DER penetration. The review begins by synthesizing multi-dimensional feature extraction techniques and cutting-edge clustering algorithms that establish the foundation for dimensionality reduction. It then delves into refined aggregation models tailored to heterogeneous resources, including dynamic data-driven equivalence for renewable generation, Minkowski sum-based boundary approximations for energy storage, and thermodynamic alongside Markov chain mapping methods for flexible loads. Building upon these models, the paper comprehensively discusses the practical applications of generalized aggregators, such as microgrids and virtual power plants, in feasible region error evaluation, coordinated network control, multi-agent market games, and privacy-preserving architectures. Finally, the review outlines future research trajectories, emphasizing hybrid data-model-driven architectures for real-time dispatch, distributionally robust optimization (DRO) for enhancing grid resilience and self-healing, and decentralized trading ecosystems to ensure equitable system-level surplus allocation. This review aims to provide a systematic theoretical reference for the coordinated management and aggregated trading of flexibility resources in novel power systems. Full article

Increasing load demand and localized constraints are driving the need for cost-effective alternatives to traditional network reinforcement. However, existing Non-Wires Alternative (NWA) planning approaches often rely on simplified assumptions or computationally intensive full-year optimization, limiting their practical applicability. This study proposes a planning-oriented method integrating 8760-h Direct Load Flow (DLF)-based assessment, worst-case screening, and Mixed-Integer Linear Programming (MILP)-based resource sizing for the coordinated deployment of Energy Storage Systems (ESSs), Demand Response (DR), and Photovoltaic (PV) resources, along with building-scale microgrid candidates. The proposed microgrid candidates are modeled as grid-connected, building-scale configurations in which PV, ESSs, and DR are co-located at a single node, representing integrated resource units within the distribution system. The results show that voltage constraints are the dominant limiting factor and that NWAs primarily function as an investment deferral strategy rather than a full replacement for traditional reinforcement, delaying constraint violations by approximately 2 to 14 years. An ESS provides the most direct contribution to constraint mitigation, while DR and PV offer complementary support. The results also highlight the importance of locational deployment. In particular, a co-located microgrid configuration (MG_111) is selected as the optimal portfolio under moderate load growth conditions (Case B, 2%), demonstrating the practical feasibility of integrated DER deployment at a single node. Economic feasibility is found to be highly sensitive to incentive design, with profitability achieved only under favorable compensation conditions. These results demonstrate that coordinated DER portfolios can effectively extend deferral periods and provide practical insights into cost-effective NWA planning under realistic operating conditions. Full article

This paper proposes a deep-learning-based scheduling approach for community microgrids that explicitly accounts for building thermal dynamics and customer comfort preferences. Traditional heating, ventilation, and air-conditioning (HVAC) scheduling models are NP-hard and scale poorly, especially for large systems with many buildings. To address this challenge, we develop a dual-encoder deep learning model that predicts building-level HVAC ON/OFF schedules using temporal load and temperature profiles, along with static building thermal parameters. The proposed model is trained in a supervised manner using solutions generated by an optimization-based HVAC scheduling framework, thereby serving as a computationally efficient surrogate for predicting HVAC schedules within a microgrid. The model is trained on samples generated by the optimization-based HVAC scheduling framework and evaluated using precision, recall, and F1-score. The results indicate strong predictive performance. Full article

This work uses battery-coupled power electronic converter systems and distributed backstepping controllers to improve the reliability of electrical distribution networks. The motivation is to prevent blackouts such as the 28 April 2025 outage in Spain, Portugal, and the south of France. It is now accepted that a rapid rise in solar power injections caused AC overvoltage above grid code limits, triggering photovoltaic (PV) park disconnections as overvoltage self-protection. This case study considers near-Zero-Energy Buildings (nZEBs) connected to the Madeira Island isolated microgrid, where PV power installation is increasing excessively. The main university facility will be upgraded as an nZEB, using roughly 3000 m² of unshaded rooftops plus coverable parking areas to install PV panels. Optimizing the profits/energy cost ratio, a PV power system of around 560 kW can be planned, and the Battery Storage System (BSS) energy capacity can be estimated. The BSS is connected to the university nZEB via backstepping-controlled multilevel converters to manage PV and BSS, enabling the building to contribute to voltage and frequency regulation. Distributed multilevel converters inject renewable energy into the medium-voltage network, regulating active and reactive power to prevent overvoltages shutting down the PV inverters. This removes sustained overvoltage and maximizes PV penetration while augmenting AC grid reliability and resilience. When there is excess solar power and reactive power is insufficient to reduce voltage, controllers slightly curtail PV active power to eliminate overvoltage, maintaining operation with minimal revenue loss while preventing long interruptions, thereby improving grid reliability and power quality. Full article

Modern microgrids increasingly rely on learning-based energy management systems (EMSs) for real-time decision-making, yet remain vulnerable to cyber–physical disturbances, sensor tampering, and model uncertainty. Existing resilient control and robust reinforcement learning methods provide useful foundations, but rarely address adversarial measurement perturbations that distort belief evolution under partial observability. This gap is critical, as structured perturbations in sensing channels can destabilize learning-based policies and propagate into voltage-regulation violations. This paper proposes an adversarially robust reinforcement learning framework for energy management with voltage regulation under partial observability in microgrids. The EMS decision-making problem is formulated as a partially observable Markov decision process (POMDP) that accounts for adversarial measurement perturbations, belief evolution, and system-level economic and voltage constraints. To avoid excessive conservatism under worst-case uncertainty, an adversary-aware belief construction based on adversarial belief balancing (A3B) is employed to focus on policy-relevant perturbations. Building on this belief representation, an adversarially robust learning framework is developed by incorporating adversarial counterfactual error (ACoE) as a learning regularization mechanism, enabling a balance between nominal operating efficiency and robustness under adversarial measurement distortion. The case study is conducted on a medium-voltage radial distribution feeder (IEEE 123-Node Test Feeder). Case study results demonstrate that the proposed ACoE-regularized policies substantially reduce voltage-deficit events, improve policy stability, and maintain operational constraints under adversarial perturbations, consistently outperforming standard proximal policy optimization (PPO)-based controllers. These results indicate that counterfactual-aware, belief-based learning substantially enhances voltage quality and operational resilience in microgrids with high penetration of distributed energy resources. Full article