摘要
配电网的拓扑结构变动频繁,负荷水平和分布式电源(distributed generator,DG)出力的不确定性使得运行场景愈加复杂多变。基于此,提出了一种基于图深度强化学习的有源配电网故障恢复方法。首先,考虑DG与负荷的时变性,构建起基于图注意力网络(graph attention network,GAT)与柔性策略-评价(soft actor-critic,SAC)算法相结合的配电网故障恢复框架,介绍故障恢复方法及其算法原理。然后,建立面向配电网故障恢复的图深度强化学习模型,通过将GAT嵌入到SAC算法的前置神经网络来提高智能体对配电网运行状态和拓扑结构的感知能力,并创新性地引入无效动作掩盖机制以规避非法动作,通过智能体与环境进行交互,寻找最优开关动作控制策略,实现高渗透率DG接入下的故障恢复趋优学习。最后,在IEEE33节点和148节点算例进行验证,并与多种基线方法进行对比测试,所提方法可以实现最快毫秒级故障恢复,具有更加高效优越的恢复效果,在拓扑变动下的负荷供电率相较于基准模型提升了4%~5%。
The topology of the distribution network changes frequently,and the uncertainty of load level and distributed generator(DG)output makes the operation scenarios more complex and variable.Based on this,a fault recovery method for an active distribution network based on graph deep reinforcement learning is proposed.Firstly,considering the time-varying characteristics of DG and load,a fault recovery framework for the distribution network based on the graph attention network(GAT)and the soft actor-critic(SAC)algorithm is constructed.The fault recovery method and its algorithm principle are introduced.Then,a graph deep reinforcement learning model for distribution network fault recovery is established.By embedding GAT into the pre-neural network of the SAC algorithm,the agent's perception ability of the distribution network operation status and topology is improved,and an invalid action masking mechanism is innovatively introduced to avoid illegal actions.Through the interaction between the agent and the environment,the optimal switch action control strategy is found to realize the optimal learning of recovery under high DG penetration.Finally,the proposed method is verified on IEEE 33-bus and 148-bus examples.Compared with multiple baseline methods,the proposed method can achieve the fastest fault recovery at the millisecond level,and has a more efficient and superior recovery effect,the load supply rate under topology change increased by 4%to 5%compared with the benchmark model.
作者
何小龙
高红均
王仁浚
罗龙波
叶萌
黄媛
刘俊勇
HE Xiaolong;GAO Hongjun;WANG Renjun;LUO Longbo;YE Meng;HUANG Yuan;LIU Junyong(College of Electrical Engineering,Sichuan University,Chengdu 610065,Sichuan Province,China;Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Guangzhou 510630,Guangdong Province,China)
出处
《电网技术》
北大核心
2025年第10期4342-4352,I0090-I0094,共16页
Power System Technology
基金
国家自然科学基金项目(52077146)。
关键词
有源配电网
分布式电源
故障恢复
图注意力网络
柔性策略-评价
无效动作掩盖
active distribution network
distribution generator
fault recovery
graph attention network
soft actor-critic
invalid action masking
