中国电机工程学报2025，Vol.45Issue(11)：4130-4143,14.DOI:10.13334/j.0258-8013.pcsee.241312
基于深度强化学习的高速公路服务区新能源充电站两阶段优化调控策略
Two-stage Optimal Dispatch Strategy of New Energy Charging Station in Highway Service Area Based on Deep Reinforcement Learning
摘要
Abstract
Aiming at the negative impact of the uncertainty of electric vehicle(EV)charging and new energy power generation on the economic,reliable,green and efficient operation of a charging station in highway service area,a two-stage optimal dispatch of a new energy charging station based on deep reinforcement learning is proposed.The establishment of wind-photovoltaic-storage charging station enhances reliability of power supply in remote areas of highway and achieves"green electricity"on-site consumption.To deal with the problem of"source-load"time dimension mismatch and take into account the global optimality and policy flexibility of regulation,a day-ahead and intra-day two-stage optimization model is established.In the day-ahead model,EVs are guided by price incentives considering user behavior characteristics.In the intra-day model,considering the diversity of energy subjects and optimization objectives,the complex multi-objective nonlinear and non-convex optimization is transformed into a multi-agent Markov game model,and the multi-agent deep reinforcement learning is used to solve it.Finally,taking a highway charging station as an example,the effectiveness and optimality of the proposed method are verified.The simulation results show that the proposed method can ensure the basic charging requirements of users,avoid congestion,and realize the economical and low-carbon operation and reliable power supply in the station.关键词
高速公路新能源充电站/两阶段优化调控/价格激励/马尔可夫博弈模型/多智能体深度强化学习Key words
new energy charging station on highway/two-stage optimal dispatch/price incentive/Markov game model/multi-agent deep reinforcement learning分类
动力与电气工程引用本文复制引用
周健树,向月,张新,刘俊勇..基于深度强化学习的高速公路服务区新能源充电站两阶段优化调控策略[J].中国电机工程学报,2025,45(11):4130-4143,14.基金项目
四川省科技计划项目(2024YFHZ0312) （2024YFHZ0312）
四川大学"从0到1"创新项目(2023SCUH0002).Science and Technology Program of Sichuan Province(2024YFHZ0312) （2023SCUH0002）
Sichuan University 0-1 Innovation Research Project(2023SCUH0002). （2023SCUH0002）
