Off-grid microgrids powered entirely by renewable energy sources face substantial challenges in achieving utility-grade reliability standards. Existing microgrid planning frameworks often prioritize cost minimization while treating reliability as a secondary metric, thereby leading to suboptimal designs. This paper presents a comprehensive scenario-based optimization framework that simultaneously addresses long-term capacity planning and short-term operational dispatch in two stages for 100

Off-grid microgrids powered entirely by renewable energy sources face substantial challenges in achieving utility-grade reliability standards owing to renewable intermittency and the absence of grid backup. Existing microgrid planning frameworks often prioritize cost minimization while treating reliability as a secondary metric, thereby leading to suboptimal designs that are vulnerable to renewable variability, component failures, and other operational uncertainties. This paper presents a comprehensive scenario-based optimization framework that simultaneously addresses long-term capacity planning and short-term operational dispatch in two stages for 100%-renewable microgrids. The developed two-stage stochastic programming model co-optimizes the investment and operation of photovoltaic generation and battery energy storage, while ensuring compliance with stringent reliability constraints following utility grid standards. Network modeling with operational constraints, such as line capacities and voltage limits, is incorporated to allow distributed resource placement leveraging power sharing between microgrid nodes. A novel scenario generation approach captures critical uncertainties, including seasonal demand fluctuations, solar output variations, and probabilistic equipment failures, through the statistical clustering of historical data. The optimization framework integrates utility-grade reliability constraints limiting the expected energy not served to below 0.002% of the annual demand while minimizing the total system costs. Numerical simulations demonstrate the effectiveness of the proposed framework, achieving approximately 99.998% supply reliability using only photovoltaic power and battery energy storage. The optimized network-aware distributed resource allocation provides inherent resilience through power rerouting during component outages, maintaining load continuity even under simultaneous equipment failures. This study confirms the feasibility of 100%-renewable microgrids to support remote communities while meeting utility-grade reliability benchmarks.

The growing integration of renewable energy sources in modern power systems has introduced significant operational challenges due to their intermittent and uncertain generation outputs. In recent years, mobile energy storage systems (ESSs) have emerged as a popular flexible resource for mitigating these challenges. Compared to stationary ESSs, mobile ESSs offer additional spatial flexibility, enabling cost-effective energy delivery through the transportation network. However, the widespread deployment of mobile ESSs is often hindered by high investment costs, which has motivated researchers to investigate more readily available alternatives, such as electric vehicles (EVs) as mobile energy storage units instead. Hence, we explore this opportunity by formulating a mixed-integer programming (MIP) based day-ahead electric vehicle joint routing and scheduling problem in this work. However, solving the problem in a practical setting can often be computationally intractable since the presence of binary variables makes it combinatorially challenging. Therefore, we propose to simplify the solution process by pruning the solution search space for a MIP solver with a transformer deep learning (DL) model. This is done by training the model to rapidly predict the optimal binary solutions. In addition, unlike many existing DL approaches that assume fixed problem structures, the proposed model is designed to accommodate problems with varying EV fleet sizes. This flexibility is non-trivial since frequent retraining can introduce significant computational overhead. Lastly, we evaluated the approach with simulations on the IEEE 33-bus and 69-bus system coupled with a 7-node and 12-node transportation network.

Modern Electric Vehicles (EVs) support two-way energy flow, allowing vehicles to both draw power from and supply power to the grid (Vehicle-to-Grid, or V2G). This capability helps reduce carbon emissions and save costs for both EV owners and the grid. The success of V2G systems relies on real-time sensor data from EVs, charging stations, and grid infrastructure, which enable precise monitoring of battery state-of-charge (SoC), grid load, and renewable energy availability. EV owners can charge using renewable energy and discharge surplus energy when renewables are unavailable, taking advantage of lower rates during off-peak hours and selling excess power back during peak demand. Existing works examine the optimal charging and discharging problem from the perspectives of aggregators (charging stations) or operators (grids). This study approaches the problem from the perspective of EV owners, focusing on the scenario where travel plans are well-known in advance. We formulate charging and discharging scheduling as a sequential decision- making process and solve it efficiently and optimally using dynamic programming. Experiments show that, in an ideal scenario where green energy is periodically available, an optimal schedule can significantly reduce costs (up to 70%) by selling surplus energy while maintaining a low carbon footprint. In real world scenario where information about price and energy generation is not available, the proposed method also consistently outperforms baselines and aligns better with user preferences.

The transition to battery electric buses (BEBs) presents new challenges to the transportation and energy sectors, necessitating meticulous decision-making for a sustainable transition. This article proposes an integrated optimization model to determine the required number of chargers, charger power, grid capacity upgrade, battery sizing, and charging schedules for a heterogeneous fleet of BEBs. The proposed battery-degradation-aware (DA) model captures the interdependencies of charger deployment, battery sizing, and battery degradation to determine the optimal decisions based on an assumed battery degradation behavior. To this end, we assume an arbitrary nonlinear degradation model and develop a tractable mixed-integer linear programming formulation using a decomposition approach and McCormick relaxation. We further account for the uncertainty of electricity prices to design a robust model. The model is then implemented for a real fleet of 78 buses with different trip schedules, and two empirical battery degradation models are employed. The results show that, considering the two degradation models, the DA model reduces the overall costs by 28.6% and 46.8% in comparison with the degradation-neutral (DN) model due to prolonging the estimated cycle life of batteries by 67% and 135% on average.

Lagrangian-based methodologies are one of the fundamental paradigms of safe reinforcement learning (RL) for constrained Markov decision processes, particularly when dealing with multi-constraint cases. While the specific details of the methodologies may differ, with some using a single estimator for the overall mixed penalty term of the constraints and others using separate estimators for the constraints, the fundamental question of the theoretical validity of the methodologies has remained largely unexplored. The present paper performs the first theoretical analysis of the methodologies and proves that the use of the mixed critic structure leads to the presence of a bias due to the target drift of the Lagrange multipliers. On the other hand, the use of the dedicated critic structure, where separate critics are used for the reward function and the constraint functions, does not suffer from this bias. The theoretical analysis is supported with experiments on a realistic power system environment with multiple constraints, where the dedicated critic structure succeeds in satisfying the constraints, whereas the mixed critic structure fails.

Accurate electricity price forecasting (EPF) is essential for market participants to support operational planning and risk management, yet remains challenging due to strong volatility, nonlinear dynamics, and frequent extreme price spikes. These challenges are particularly pronounced in the Australian National Electricity Market (NEM), where high renewable penetration further increases uncertainty. This paper investigates week-ahead electricity price forecasting and proposes a hybrid KAN+XGBoost framework that integrates Kolmogorov-Arnold Networks (KAN) with tree-based learning. The proposed approach combines the global nonlinear representation capability of KAN with the local robustness of XGBoost to capture both long-term dependencies and short-term price fluctuations. Experiments are conducted on real-world NEM data using an expanding window evaluation strategy. The results demonstrate that the proposed model outperforms benchmark methods, including SARIMAX, Long Short-Term Memory (LSTM), standalone KAN, and XGBoost, reducing MAE by approximately 12

Reliable operation is a central motivation for deploying renewable-based microgrids, yet reliability is frequently treated as a secondary outcome of cost-driven design rather than as a governing planning objective. Existing reviews remain fragmented across techno-economic sizing, optimization methods, and reliability assessment, limiting the translation of planning outcomes into operationally reliable systems. This paper presents a systematic rapid review that positions reliability as the central organizing principle for microgrid design. Specifically, this review systematically synthesizes recent literature to examine how planning assumptions, optimization formulations, operational flexibility mechanisms, and reliability assessment frameworks jointly shape reliability outcomes. The synthesis shows that reliability in renewable-based microgrids is governed primarily by chronological, time-coupled energy adequacy rather than installed capacity alone, with Dunkelflaute events emerging as a key determinant of adequacy failure. Reliability outcomes are shaped by the joint interaction of resource portfolios, storage operating policies, and state trajectories, network features, and protection feasibility under inverter-dominated operation. The review further demonstrates that reliability indices inherited from conventional power systems are poorly suited for renewable-based microgrids, as they compress performance into single dimensions and obscure temporal, spatial, and service-critical risk concentrations. Across optimization practice, reliability is increasingly embedded through multi-objective and constrained formulations; however, persistent gaps remain in representing correlated renewable scarcity, mission-profile-dependent component reliability, and interruption valuation (e.g., value of lost load and customer damage functions) in a consistent and decision-relevant manner. Overall, this review consolidates planning factors, optimization approaches, reliability evaluation methods, and metric suitability into an integrated roadmap for reliability-centered microgrid planning, and outlines future directions toward state-aware, service-oriented planning and assessment frameworks.

Vehicle-to-vehicle (V2V) energy trading enables decentralized peer-to-peer energy exchange among electric vehicles (EVs), reducing grid dependency while monetizing surplus capacity. However, coordinating self-interested EV agents with diverse charging needs and uncertain arrival-departure schedules remains challenging. Existing approaches either require centralized optimization with computational limitations or lack fairness guarantees. This paper integrates Nash Bargaining Solution into Multi-Agent Deep Deterministic Policy Gradient, namely Nash-MADDPG, for incentive-aligned V2V energy trading. Nash bargaining determines efficient bilateral pricing, while Nash-guided price proximity rewards align agent learning toward bargaining-optimal strategies. Evaluation over 30-day continuous operation demonstrates an improvement of 61.6

As power systems advance toward net-zero targets, behind-the-meter renewables are driving rapid growth in distributed energy resources (DERs). Virtual power plants (VPPs) increasingly coordinate these resources to support power distribution network (PDN) operation, with EV charging stations (EVCSs) emerging as a key asset due to their strong impact on local voltages. However, in practice, VPPs must make operational decisions with only partial visibility of PDN states, relying on limited, aggregated information shared by the distribution system operator. This work proposes a safety-enhanced VPP framework for coordinating multiple EVCSs under such realistic information constraints to ensure voltage security while maintaining economic operation. We develop Transformer-assisted Lagrangian Multi-Agent Proximal Policy Optimization (TL-MAPPO), in which EVCS agents learn decentralized charging policies via centralized training with Lagrangian regularization to enforce voltage and demand-satisfaction constraints. A transformer-based embedding layer deployed on each EVCS agent captures temporal correlations among prices, loads, and charging demand to improve decision quality. Experiments on a realistic 33-bus PDN show that the proposed framework reduces voltage violations by approximately 45

The wide adoption of residential photovoltaic (PV) systems introduces new challenges for generation fraud detection (FD). Unlike traditional electricity theft detection, which focuses on electricity consumption-side behavior, PV generation fraud detection (PVG-FD) is complicated by the inherent intermittency and uncertainty of PV generation. The distributed nature of PV systems poses further challenges for centralized PVG-FD approaches due to scalability and privacy concerns. This paper develops a privacy-preserving distributed PVG-FD framework based on federated learning (FL). In this framework, a utility company manages multiple household communities, where each of which is equipped with a local detector. The framework integrates a novel detection model architecture with privacy-preserving global collaboration. Each community’s local model fuses PV generation and weather data via a co-attention mechanism to detect discrepancies critical for PVG-FD. The FL framework enables cross-community collaboration by aggregating model parameters and prototypes, leveraging global knowledge sharing with local refinement while preserving privacy. It also uses prototype alignment to address class imbalance by enhancing fraud sample representation. Extensive experiments on a real-world residential PV dataset validate the effectiveness of the developed method and demonstrate that it outperforms state-of-the-art FL methods across various scenarios. The results also show its scalability across varying community sizes and strong robustness to class imbalance.

Accurate electricity load forecasting is a crucial prerequisite for stable power system operations. While prevalent deep learning models present competitive performance, they often operate as black boxes and lack interpretabil ity. However, such capability has increasingly become a key enabler to understand the influences of forecast drivers, thereby assisting more informed system operations. While the Kolmogorov-Arnold network (KAN) has emerged as a promising alternative because of its learnable activation function design, its direct application to time-series forecasting faces challenges in modeling complex temporal data patterns. Also, simple integration into existing architectures, such as serving as replacement for neural modules, cannot fully leverage KAN's in terpretability strengths. To address these gaps, this study develops LoadKAN, a novel hybrid and interpretable framework for load forecasting that synergistically combines a specifically-designed feature-isolated temporal at tention mechanism with a KAN module. The attention stage aims to extract temporal dynamics from each input feature independently, such as historical load and human mobility, providing distilled feature representations to the KAN module for interpretable predictions. When evaluated on datasets from three representative U.S. elec tricity markets, our LoadKAN remains highly competitive when compared to extensively-tuned, state-of-the-art, black-box deep learning benchmarks. More importantly, LoadKAN's interpretability enables a granular analy sis of the learned non-linear relationships between six distinct mobility patterns and electricity load. Through KAN-learned activation functions, our quantitative sensitivity analyses on mobility features reveal complex and market-specific dependencies. These findings further demonstrate the ability of our LoadKAN to generate insights often obscured by opaque black-box neural forecasting models.

Distributed renewable energy (DRE) systems, such as so larpanels, wind turbines, and small-scale hydroelectric systems, are increasingly participating in electricity markets. The unpredictable nature of renewable energy imposes a significant impact on the strategic offering decisions of DRE producers in two-settlement electricity markets. Furthermore, small-scale DRE producers face challenges, such as minimum size threshold requirements, that prevent them from par ticipating in wholesale electricity markets. Driven by these issues, this work proposes a blockchain-aided coalitional game framework to enable the cooperative renewable offering strategies of distributed producers, wherein these producers are incentivized to form a grand coalition to participate in electricity markets and share real-time balancing risks. Moreover, it is verified that the grand coalition is optimal for maximizing the total profit of the producers, indicating the benefit of cooperation. It is challenging to obtain the core of the coalition due to the huge computational complexity. Nevertheless, a closed-form profit allocation mechanism is constructed and proved to be in the core of the coalition. This indicates that none of these producers has an incentive to leave the grand coalition. Furthermore, we design a smart contract to automate the coalition formation and profit allocation processes of DRE producers on the blockchain. Finally, numerical studies are conducted to validate the established theoretical results. Simulation results show that the proposed approach increases individual utility for all participants and improves the system's overall profit by up to 9.4% compared with the independent baseline.

​​Peer-to-peer (P2P) energy trading is a promising mechanism for coordinating renewable-rich residential smart grids, but its real-time operation is challenged by uncertain photovoltaic generation, household demand, and ambient temperature. This paper proposes a distributed scenario-based model predictive control (MPC) framework for P2P energy trading with heating, ventilation, and air-conditioning (HVAC) flexibility. The framework models HVAC thermal inertia as a demand-side flexibility resource and coordinates grid exchange, P2P trading, flexible load scheduling, and HVAC control in a rolling-horizon manner. At each control instant, correlated uncertainty scenarios are generated from forecast residuals, a finite-horizon stochastic optimization problem is solved, and only the non-anticipative first-step decision is implemented. To support scalable smart-grid operation, the resulting problem is decomposed across prosumers and solved by a proximal Jacobian alternating direction method of multipliers (PJ-ADMM). The distributed algorithm enables parallel prosumer updates, uses a closed-form market-clearing projection, and requires only P2P trading trajectories to be exchanged with a lightweight coordinator. Case studies based on residential load and solar data show that the proposed controller approaches the performance of centralized scenario-based MPC while reducing the computational latency of sequential distributed optimization. Compared with deterministic MPC, it lowers operating cost, power mismatch, and comfort violation, and its average and 95th-percentile solve times remain well within a 15-minute control interval.

Weak grid (WG) is an interface power constraint which weakens the voltage and frequency stability of nodes. The virtual synchronous generators (VSGs) operating in parallel in a WG system face frequency instability, and potential low-frequency oscillations may lead to grid collapse. To address this challenge, this paper proposes a time delay correction (TDC) scheme to strengthen the stability of VSGs in WG. First, this paper proposes a power small-signal decoupling method for parallel VSGs. Secondly, a voltage source model of weak grid dominated by synchronous generators is constructed based on the renewable energy station short circuit ratio (RSCR) of new energy field stations. Then, to improve the synchronization stability of the system, we enhance the control strategy of the VSG by connecting a time-delay correction algorithm in series at the active power input. Through hardware-in-the-loop experiments, the TDC scheme significantly reduces the frequency fluctuation of the three parallel VSG system by 57.45% to 82.16% compared with the conventional strategy. In addition, the stability of TDC outperforms the conventional strategy as well as the existing improved strategies under lower short-circuit ratios.

The rapid growth of electric vehicles (EVs) requires more effective charging infrastructure planning. Infrastructure layout not only determines deployment cost, but also reshapes charging behavior and influences overall system performance. In addition, destination charging and en-route charging represent distinct charging regimes associated with different power requirements, which may lead to substantially different infrastructure deployment outcomes. This study applies an agent-based modeling framework to generate trajectory-level latent public charging demand under three charging regimes based on a synthetic representation of the Melbourne (Australia) metropolitan area. Two deployment strategies, an optimization-based approach and a utilization-refined approach, are evaluated across different infrastructure layouts. Results show that utilization-refined deployments reduce total system cost, accounting for both infrastructure deployment cost and user generalized charging cost, with the most significant improvement observed under the combined charging regime. In particular, a more effective allocation of AC slow chargers reshapes destination charging behavior, which in turn reduces unnecessary reliance on en-route charging and lowers detour costs associated with en-route charging. This interaction highlights the behavioral linkage between destination and en-route charging regimes and demonstrates the importance of accounting for user response and multiple charging regimes in charging infrastructure planning.

Electric vehicles (EVs) are essential for sustainable urban mobility, coordinating transportation demands with energy distribution networks. However, uncoordinated EV charging neglects trip chain continuity, inducing spatial-temporal congestion and overloading local charging capacities. Thus, effectively guiding EVs is a key problem in mitigating traffic emissions and preventing power grid-side stress. In this paper, a two-stage dynamic routing framework within a traffic-energy coordination architecture is proposed, integrating an AHP-Entropy-TOPSIS model for station selection and an Improved Ant Colony Optimization algorithm for trajectory execution. Using this framework, a series of macro-micro simulations on the Sioux Falls network was conducted alongside a congestion-driven dynamic pricing mechanism. The results indicate that the pricing strategy facilitates spatial load balancing through peak shaving at core nodes. Compared to conventional standard meta-heuristic baselines, this framework reduces average economic costs by 28.9% while ensuring battery safety and limiting indirect carbon emissions. The proposed framework provides a multi-objective navigation solution that prevents cross-layer decision fragmentation, supporting the sustainable development of smart city infrastructure.

In real-time networked applications such as cyber-physical systems (CPS), the Age of Information (AoI) has emerged as an important metric for evaluating information timeliness. Mobile edge computing (MEC) provides a promising solution for supporting computation-intensive CPS applications, such as smart manufacturing, while reducing AoI. We study the timeliness of compute-intensive updates and jointly optimize task-updating and offloading policies under dynamic edge loads to minimize the expected time-average AoI. This problem is challenging because of the fractional AoI objective and asynchronous decision-making in the semi-Markov game (SMG). To address these challenges, we propose a fractional reinforcement learning (RL) framework. We first develop a fractional single-agent RL framework and establish its linear convergence rate. We then extend the framework to the multi-agent setting, generalize Dinkelbach’s method, and show that the resulting update is equivalent to an inexact Newton method. We further derive sufficient conditions for local linear convergence to a Nash equilibrium (NE). Based on this framework, we design an asynchronous model-free fractional multi-agent deep RL algorithm that enables each mobile device to make task-updating and offloading decisions without knowing the real-time system dynamics or other devices’ decisions. Experiments show that the proposed algorithm reduces the average AoI by up to 42.0% compared with the best existing baseline.

Accurate electric vehicle (EV) charging demand forecasting is essential for stable grid operation and proactive EV participation in electricity market. Existing forecasting methods, particularly those based on graph neural networks, are often limited to modeling pairwise relationships between stations, failing to capture the complex, group-wise dynamics inherent in urban charging networks. To address this gap, we develop a novel forecasting framework namely HyperCast, leveraging the expressive power of hypergraphs to model the higher-order spatiotemporal dependencies hidden in EV charging patterns. HyperCast integrates multi-view hypergraphs, which capture both static geographical proximity and dynamic demand-based functional similarities, along with multi-timescale inputs to differentiate between recent trends and weekly periodicities. The framework employs specialized hyper-spatiotemporal blocks and tailored cross-attention mechanisms to effectively fuse information from these diverse sources: views and timescales. Extensive experiments on four public datasets demonstrate that HyperCast significantly outperforms a wide array of state-of-the-art baselines, demonstrating the effectiveness of explicitly modeling collective charging behaviors for more accurate forecasting.