湖北电力2025,Vol.49Issue(2):1-10,10.DOI:10.3969/j.issn.1006-3986.2025.02.001
基于柔性行动器-竞争评判器算法的微电网优化调度方法
Microgrid Optimization Scheduling Method Based on Soft Actor-Dueling Critic Algorithm
摘要
Abstract
To address the issue of the optimal scheduling of microgrids with source-load uncertainties,this paper proposes a microgrid optimal scheduling method based on the soft actor-dueling critic(SADC)algorithm.Firstly,the minimization of the operating cost of the microgrid system is taken as the optimization objective,and the power balance of the system,the operating characteristics of the equipment,etc.as the constraint conditions,a microgrid optimization scheduling model is established.Secondly,the dueling network mechanism is adopted to improve the critic structure of the SAC algorithm,and then the improved SADC algorithm is used to solve the microgrid optimization scheduling model with source-load uncertainty.Finally,based on the microgrid calculation examples,the SADC algorithm is applied to determine the optimization scheduling strategy,verifying the effectiveness and superiority of the SADC algorithm.The simulation results show that,compared with the existing DQN,DDPG and SAC algorithms,the SADC algorithm reduces the operating cost by 19.75%,10.18%and 3.59%respectively,and performs better in the robustness of microgrid optimization scheduling.关键词
可再生能源/微电网/深度强化学习/柔性行动器-评判器/竞争网络/优化调度Key words
renewable energy/microgrid/deep reinforcement learning/soft actor critic/dueling network/optimal scheduling分类
信息技术与安全科学引用本文复制引用
BAO Gang,ZHOU Ranran,YUAN Hao,LI Yong..基于柔性行动器-竞争评判器算法的微电网优化调度方法[J].湖北电力,2025,49(2):1-10,10.基金项目
国家自然科学基金资助项目(项目编号:62476153). (项目编号:62476153)