基于图强化学习的配电网故障恢复决策OACSTPCD
Fault Recovery Decision of Distribution Network Based on Graph Reinforcement Learning
针对配电网拓扑变化时启发式等算法在配电网故障恢复决策中求解效果与适应性变差的问题,提出了一种基于图强化学习的故障恢复决策方法.首先,利用图数据表征故障恢复中的决策信息,包括配电网拓扑结构与电气特征信息.然后,在图强化学习模型中设置前置图神经网络接收图数据输入,应对故障恢复过程中配电网的拓扑变化.最后,由内嵌图神经网络的强化学习智能体输出最终故障恢复策略以提高决策速度.采用改进的PG&E 69节点配电网算例进行验证,结果表明所提算法求解速度…查看全部>>
To solve the problem that the effectiveness and adaptability of heuristic algorithms in distribution network fault recovery decision become poor when the topology of distribution network changes,a fault recovery decision method based on graph reinforcement learning is proposed.First,the graph data is used to characterize the decision information in fault recovery,including distribution network topology and electrical characteristics.Then,the pre-graph neural…查看全部>>
张沛;陈玉鑫;王光华;李晓影
北京交通大学电气工程学院,北京市 100044北京交通大学电气工程学院,北京市 100044国网河北省电力有限公司保定供电分公司,河北省保定市 071000国网河北省电力有限公司保定供电分公司,河北省保定市 071000
图强化学习图神经网络强化学习配电网故障恢复
graph reinforcement leaninggraph neural networkreinforcement learningdistribution networkfault recovery
《电力系统自动化》 2024 (2)
151-158,8
国家电网有限公司科技项目(kj2021-014). This work is supported by State Grid Corporation of China(No.kj2021-014).
评论