| 杨 莹,刘启航,赵为光,苏勋文,李学军,张 帅,聂兴鹏.基于深度强化学习的光氢储新能源汽车充能站优化调度[J].电力需求侧管理,2025,27(4):92-97 |
| 基于深度强化学习的光氢储新能源汽车充能站优化调度 |
| Optimization scheduling of photovoltaic-hydrogen-storage for new energy vehicle charging station based on deep reinforcement learning |
| 投稿时间：2025-03-28 修订日期：2025-05-12 |
| DOI：10. 3969 / j. issn. 1009-1831. 2025. 04. 014 |
| 中文关键词: 光氢储充能站 新能源汽车 双层顺序优化调度 分时电价 深度强化学习 |
| 英文关键词: PV-hydrogen-storage charging station new energy vehicles two-layer sequential optimization scheduling time-of-use pricing deep reinforcement learning |
| 基金项目:国家自然科学基金资助面上项目（51677057）；湖南省重点研发计划资助项目（2023SK2078） |
|
| 摘要点击次数: 720 |
| 全文下载次数: 555 |
| 中文摘要: |
| 针对新能源汽车充能时间不确定性、光伏出力随机性下充能站运营成本高的问题,同时应对大规模电动汽车（electric ve?hicle,EV）充电过程中动作变量过多的挑战,提出了一种基于深度强化学习（deep reinforcement learning,DRL）算法的光氢储充能站双层顺序优化调度模型。考虑光伏出力、分时电价、负荷不确定性和系统各设备运行效率等因素,以满足用户需求和降低充能站运营成本为目标,采用双延迟深度确定性策略梯度算法（twin delay deep deterministic policy gradient,TD3）对双层顺序调度模型进行求解。仿真结果表明：在满足用户充能需求前提下,该模型能大幅减少充能站运营成本；此外,充电桩数量增加时,模型实时调度时间不受影响且能有效减少弃光量。 |
| 英文摘要: |
| To address the high operating costs of charging stations due to the uncertainty of charging times for new energy vehicles and the randomness of photovoltaic（PV）output, as well as to tackle the challenge of excessive action variables in large-scale electric vehicle （EV）charging processes, a two-layer sequential optimization scheduling model for a PV-hydrogen-storage charging stationis is proposed based on a deep reinforcement learning（DRL）algorithm. This model considers factors such as PV output, time-of-use pricing, load uncertainty, and the operational efficiency of each piece of equipment in the system, aiming to meet user demands while reducing the operating costs of the charging station. The twin delayed deep deterministic policy gradient（TD3）algorithm is employed to solve the two-layer sequential scheduling model. The simulation results show that the model can greatly reduce the operating cost of charging station under the premise of meeting the charging demand of users. In addition, when the number of charging piles increases, the real-time scheduling time of the model is not affected and solar curtailmentcan be effectively reduced. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|