TL;DR
An intelligent Model Predictive Control framework for optimal power flow management in microgrids, with the objective of enhancing operational resilience, reducing diesel fuel consumption, and preventing blackouts through coordinated electric vehicle (EV) charging and discharging is proposed.
Hybrid microgrids integrating photovoltaic (PV) arrays, wind tur-binedriven PMSG units, fuel cells, and battery storage enhance sustainability but face serious power quality (PQ) challenges due to the intermittent and nonlinear behavior of renewable sources and loads. Traditional PI, PR, and hybrid intelligent controllers offer acceptable nominal performance but lack adaptability and predictive capability under rapidly varying disturbances. To overcome these limitations, this paper proposes a Deep Reinforcement Learning (DRL) frame-work based on the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm for real-time PQ management, where a multi-objective reward function guides optimal actions for voltage regulation, harmonic suppression, unbalance mitigation, and frequency stability. Vali-dation in a MATLAB/Simulink hybrid microgrid with nonlinear loads and renewable intermittency shows that the proposed DRL controller reduces THD from 8.42% to 2.11%, VUF from 3.9% to 0.7%, and frequency deviation from 0.42 to 0.08 Hz, while improving settling time by nearly 50%. Convergence and multi-run statistical analysis further confirm the robustness, stability, and reproducibility of the trained policy, demonstrating the effectiveness of DRL as an intelligent and scalable solution for next-generation microgrid PQ control.
The increasing integration of renewable energy and distributed resources makes accurate forecasting essential for reliable and efficient microgrid energy management; however, existing TFT-based forecasting studies primarily focus on prediction and lack direct integration with predictive control and cyber-resilient operation. Therefore, this study proposes a TFT-MPC-CR framework that combines Temporal Fusion Transformer (TFT) forecasting, Model Predictive Control (MPC), AI-based False Data Injection (FDI) detection, and adaptive resilient control. The framework is implemented in Python using PyTorch, with the Microgrid PV-EV Charging Dataset obtained from Kaggle, where PV generation, load demand, battery SOC, EV charging, and grid variables are used for learning. TFT predicts future PV generation and energy demand, and MPC optimizes battery, EV, and grid power allocation, while the cybersecurity layer detects manipulated measurements and activates resilient MPC. As a target experimental outcome, the proposed framework is designed to achieve at least 5–10% lower forecasting error than conventional TFT and improve operational resilience under FDI attacks. The framework is expected to provide accurate prediction, efficient energy management, rapid attack response, and secure autonomous microgrid operation.
HVAC systems represent a major share of building energy consumption. Traditional control strategies are limited in coordinating energy-comfort tradeoffs across multiple zones simultaneously. Reinforcement learning (RL) offers adaptive, data-driven control that optimizes performance over time. However, deploying learned neural network controllers in safety-critical building systems remains challenging due to lack of formal safety guarantees. We propose a safety-certified deep RL framework for multi-zone residential HVAC control. Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents are trained in an EnergyPlus/Sinergym simulation to minimize energy consumption while maintaining thermal comfort. Post-training safety certification is performed on the PPO policy using Lipschitz-based forward invariance analysis, building on existing tools for the computation of Lipschitz constants for neural networks, to guarantee constraint satisfaction. Both agents are evaluated over an annual simulation cycle in an eight-zone variable refrigerant flow (VRF) testbed. The PPO agent achieves 67\% comfort violation reduction compared to rule-based control, while the SAC agent achieves 27.6\% energy savings. The PPO policy satisfies formal safety certification with a margin of $2.003^\circ$C. These results demonstrate the feasibility of combining reinforcement learning with post-training safety verification for multi-zone building control.
The increasing integration of renewable energy sources into microgrids has intensified the need for intelligent energy management strategies capable of addressing the intermittency of solar and wind generation while ensuring reliable and cost-effective operation. Although Rule-Based Control (RBC) methods are straightforward to implement, their limited adaptability often leads to suboptimal utilisation of Hybrid Energy Storage Systems (HESS). This study develops and evaluates a Deep Reinforcement Learning (DRL)-based energy management system employing a Deep Q-Network (DQN) to coordinate battery–supercapacitor operation within a renewable microgrid. A Gymnasium-compatible simulation environment was constructed using a publicly available time-series dataset comprising renewable generation, load demand, electricity prices, battery state of charge (SoC), and supercapacitor SoC. Feature engineering, incorporating sinusoidal temporal representations and Min-Max normalisation, was applied to enhance learning stability and capture cyclical demand and generation patterns. The DQN agent was trained over 50 episodes and benchmarked against a conventional RBC strategy under identical operating conditions. Training performance demonstrated progressive policy improvement, with cumulative rewards increasing from approximately -1200 to -400, indicating enhanced decision-making capability during learning. The learned controller exhibited adaptive energy scheduling through dynamic utilisation of the supercapacitor and selective grid interaction in response to varying operating conditions, whereas the RBC followed a deterministic control strategy with limited flexibility. However, comparative evaluation revealed that the DQN did not consistently outperform the RBC in cumulative economic performance, suggesting the need for further refinement of the reward function, training process, and hyperparameter configuration. Nevertheless, the proposed framework demonstrates the feasibility of applying deep reinforcement learning to coordinated battery–supercapacitor energy management and highlights its potential to enhance operational flexibility and intelligent resource utilisation in renewable microgrids. The study contributes a dataset-driven reinforcement learning framework that provides a foundation for future research on advanced AI-based energy management systems and the integration of more sophisticated reinforcement learning algorithms for resilient and sustainable microgrid operation.
The transition toward reliable and sustainable microgrids in constrained power systems requires both accurate load demand forecasting and the intelligent resource coordination. The primary objective of this study is to optimize the capacity sizing and operational resilience of such systems by proposing an Artificial Intelligence-driven Load Forecasting and Battery-Integrated Energy Management approach, structured around a DC-coupled solar-plus-storage (DC-CS-P-S) architecture. To accurately capture the complex thermodynamic and behavioural patterns driving electricity consumption, a multivariate long short-term memory (LSTM) network was developed. The proposed strategy physically decouples energy storage recovery from the grid by dedicating solar photovoltaic generation strictly to charging the battery energy storage system to ensure availability for peak shaving and essential load protection. Evaluated over an 8760-hour simulation, the LSTM forecasting achieved high predictive accuracy with a mean absolute percentage error of 3.31% and an RMSE of 12.39 kW. Under severe bottleneck constraints, the DC-coupled battery actively contributed 93.64 kW of peak shaving power, successfully diverting 100% of the energy deficit (135 020 kWh) entirely to non-essential infrastructure. Furthermore, a comprehensive techno-economic parametric analysis, incorporating a value of lost load reliability penalty, and a $50/ton carbon price, identified 330 kW as the absolute optimal grid capacity. At this threshold, the microgrid achieves complete reliability with zero energy shedding while maintaining a minimized baseline operational costs of $92 033 USD. Ultimately, the results demonstrate that intelligently maximizing zero-emission resources actively suppresses compounding carbon liabilities (averting a 21.6% financial premium), providing system planners with a resilient, data-driven methodology to optimize infrastructure investments without over-sizing centralized grid connections.