Jul 2026· International Conference on Control, Decision and Information Technologies· pp. 951-956· 0 citations· 16 references
Abstract
Hybrid renewable power plants that combine multiple generation technologies with energy storage can improve renewable utilization and reliability, but their operation requires solving a high-dimensional, sequential dispatch problem under uncertainty. This paper presents a reinforcement learning (RL) framework for operational dispatch of a hybrid concentrated solar power (CSP)–wind system–Photo Voltaic (PV) solar system equipped with thermal energy storage (TES) and a battery energy storage system (BESS). We reformulate operational dispatch as a Markov decision process (MDP) with continuous control actions and a feasibility-projection layer that maps agent actions to physically admissible power flows. Proximal policy optimization (PPO) is adopted to learn a closed-loop dispatch policy that can react to variability in demand and renewable output. Using an 8064-hour held-out evaluation horizon, PPO with a nominal loss-of-load penalty improves the shaped return by 4.80% relative to a fixed-priority rule-based baseline, but increases loss of power supply probability (LPSP) from 3.60% to 11.17% due to near-elimination of BESS cycling. Increasing the loss-of-load penalty recovers the baseline reliability (LPSP 3.60%) and curtailment (42.25%), but causes PPO to collapse to the rule-based policy. These results highlight the sensitivity of RL dispatch to reward weights and motivate constrained/safe-RL formulations that enforce reliability targets while optimizing storage usage.
This paper proposes a day-ahead scheduling framework to analyze and optimize the impact of the coordinated active and reactive power management of wind turbines (WTs) and battery energy storage systems (BESSs) on the energy losses and CO2 emissions of AC microgrids (MGs). Within this framework, the BESS plays a central role by absorbing surplus renewable generation, mitigating curtailment, supporting voltage regulation, and ensuring a stable and reliable dispatch over a 24-hour horizon. A population-based genetic algorithm (PGA) is proposed as the main solution methodology, while particle swarm optimization (PSO) and the multiverse optimizer (MVO) are employed as benchmark methods for comparison. To ensure a fair assessment, all optimization techniques are implemented under the same parallel processing scheme, using the same decision-variable encoding, feasibility correction procedure, and hourly sequential AC power-flow method. The objective is to minimize network energy losses and CO2 emissions under both grid-connected and islanded operating modes. The proposed methodology is validated on 33-node and 69-node MGs, both evaluated under variable demand and wind-generation scenarios to capture the uncertainty and temporal variability associated with renewable production and load behavior. In addition, the BESS model includes charging/discharging efficiency, self-discharge effects, and battery lifetime assessment under the proposed operating scenarios, allowing a more realistic representation of storage performance. The optimization methods are evaluated over 100 independent runs using the best solution, average solution, standard deviation, and computational time as performance indicators. The results show that the proposed PGA provides the most robust and repeatable performance, while also highlighting the operational contribution of the BESS, reducing renewable curtailment, and guaranteeing compliance with all technical constraints, under deterministic baseline operation and under uncertain time-varying operating conditions in both test systems.
D. Sanín-Villa, Héctor Pinto Vega, Carlos R. Baier et al.· PLoS ONE· 0 citations
The presence of intermittent sources of renewable energy in power systems requires ESSs to manage temporal imbalance in energy supply and demand. In this study, we introduce a hybrid energy storage system (HESS) coupled with an AI energy management system (EMS) that uses deep reinforcement learning (DRL) for optimal scheduling of renewable energy utilization within grid-connected and islanded microgrids. AI-enabled EMS utilizes a DRL agent with proximal policy optimization (PPO) to make optimal decisions regarding energy generation based on state space and economic considerations, while accounting for SoC constraints of batteries. An important aspect of the proposed system is the design of HESS architecture and reward function based on DRL. Further improvements are made via analysing the PPO clipping sensitivity, Pearson correlation analysis on the relationship between the intermittency of renewables and response latency, and Monte Carlo uncertainty analysis with a 95% confidence interval. For a 24-hour simulation period, the developed system is able to cut down on grid power imports by 43.2%, have an 87.3% renewable energy utilization rate, extend the lifespan of the battery from 8.1 to 12.5 years, and have 91.4% peak shaving efficiency through 100 Monte Carlo runs and without any SoC violations (25%–90%). Net benefit analysis is estimated to be $56,000–$66,000 for 15 years at a 6% discount rate, while a 120 ms response time and one-way ANOVA with Tukey's HSD confirm statistical significance.
Lalit Sachdeva, U. Anand· Energy Storage and Conversio...· 0 citations
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.
Daniel Owusu· American Journal of Neural N...· 0 citations
Microgrids must efficiently manage energy under uncertainties in renewable generation and load demand to ensure reliable and cost-effective operation. This paper investigates a microgrid system that involves renewable energy through the photovoltaic system, wind system, battery energy storage, and local load requirement with a centralized energy management system. The inflexible nature of traditional rule-based and optimizationbased approaches to solving problems can often create issues in reflection to dynamic operating conditions, and reinforcement learning approaches can produce unsafe control behavior in exploration stages. To address these issues, this paper suggests a hierarchical hybrid energy management structure that will integrate rule-based supervision and a SARSA reinforcement learning controller. Supervisory layer ensures that the system is safe by ensuring that there are operational limits such as battery state of charge limits as well as power balance conditions. The learning agent on the other hand optimizes the control choices to reduce operational costs and grid energy consumption. The outcomes of the simulation indicate that the suggested approach saves more money, learns quicker, and operates a microgrid in a stable way compared to stand alone rule-based and reinforcement learning techniques. The findings demonstrate that deterministic safety rules with adaptive reinforcement learning is an effective and helpful approach to managing energy in smart microgrids.
S. Sreekanth, P. Kiran· International Conference on...· 0 citations
ABSTRACT Ultra-fast electric vehicle (EV) charging stations operating at power levels above 350 kW introduce critical challenges related to grid peak demand, high operating cost, renewable intermittency, and battery stress. This paper presents a machine learning-enabled energy management system for a hybrid renewable-powered ultra-fast charging station integrating photovoltaic generation, battery energy storage system, dispatchable auxiliary sources, and grid supply. The proposed EMS operates at a supervisory level and coordinates energy flows under stochastic EV charging demand, time-varying electricity tariffs (₹4–₹10/kWh), and uncertain renewable generation. A learning-based decision framework is developed using a reinforcement learning policy trained over 150 episodes, incorporating renewable and EV demand forecasts with ±10% uncertainty. The EMS performs multi-objective optimization by minimizing grid energy cost and peak power demand while achieving a balanced trade-off between renewable energy utilization, grid stability, and economic performance, and maintaining battery state-of-charge within safe operating limits (0.2–0.9). Simulation results over a 24-hour operating horizon demonstrate that the proposed ML-EMS achieves a 20–35% reduction in total grid energy cost, 25–40% peak grid power reduction, and achieves a balanced trade-off between renewable utilization, grid stability, and economic performance compared to a conventional rule-based EMS. The results validate the effectiveness of machine learning-driven energy management for reliable, grid-friendly, and cost-efficient operation of next- generation ultra-fast EV charging infrastructure.
K. Reddy, Mallapu Vijaya Kumar· Matéria· 0 citations
Continuous active power dispatch is a critical task for virtual power plants (VPPs) with energy storage, particularly under the increasing uncertainty of renewable generation and the growing demand for real-time coordination in smart energy systems. This study proposes an improved Deep Deterministic Policy Gradient (DDPG)-based optimization framework to enhance continuous dispatch performance for VPPs integrating wind power, photovoltaic generation, and battery energy storage. A multi-objective scheduling model is established by jointly considering dispatch cost, renewable energy utilization, and operational constraints, while priority experience replay, cross-attention mechanisms, gradient clipping, and cosine learning-rate decay are incorporated to improve training efficiency and policy stability. Simulation results demonstrate that the proposed approach significantly outperforms conventional methods by reducing average daily dispatch costs by 16.6%, achieving a renewable energy utilization rate of 96.8%, and maintaining rapid power balance recovery under highly volatile operating conditions. The optimized dispatch strategy further improves system robustness and dynamic adaptability in scenarios involving renewable fluctuations and sudden load variations. Beyond intelligent energy management, the proposed framework provides a practical optimization methodology for communication-enabled smart grids and distributed electromagnetic sensing infrastructures, where reliable information exchange and adaptive control are essential for coordinated operation of energy and wireless network resources.
W. Liang, Y. H. Liu, Y. You et al.· Advanced Electromagnetics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
