Optimization and control of integrated energy systems based on multiagent deep reinforcement learning

作者：Hao Shen, Qingrong Liu, Qiang Zhang, Meng Zhang, Xiaoyu Liu, Yingjun Ruan, Fanyue Qian, Tingting Xu, Meng Hua, Yuting Yao · 年份：2025 · DOI：10.1117/12.3066781 · 研究领域：Power Systems and Renewable Energy、Energy Load and Power Forecasting、Smart Grid and Power Systems

This study presents a multi-agent deep reinforcement learning framework utilizing the MATD3 algorithm to enhance the control scheduling of energy systems. The proposed approach effectively integrates the benefits of energy power storage stations while minimizing the overall costs associated with energy production and distribution. By employing a collaborative multi-agent strategy, this method mitigates biases towards any individual stakeholder, ensuring a fair and efficient scheduling process. The results demonstrate the potential of MATD3 in achieving optimized performance in complex energy systems, contributing to smarter energy management strategies and fostering sustainable energy practices.