南方电网技术2024，Vol.18Issue(11)：67-78,12.DOI:10.13648/j.cnki.issn1674-0629.2024.11.008
基于图神经网络与强化学习的配电网电压与无功功率优化方法
Voltage and Reactive Power Optimization Method for Distribution Networks Based on Graph Neural Network and Reinforcement Learning
摘要
Abstract
High propotional distributed photovoltaic integration changes the operation mode of the distribution networks,and leads to a series of problems such as excessive active power losses,reduced service life of regulating equipment,and exceeding node voltage limits in the distribution networks.Based on this background,firstly the voltage and reactive power optimization problem is modelled as a Markov decision process,which is solved by using a model-free deep reinforcement learning method that captures the intermit-tence of PV and load fluctuation from historical operating data.A graph convolutional network-proximal policy optimization(GCN-PPO)algorithm is proposed which improves the perception of reinforcement learning agent on graph data of distribution networks by embedding the graph convolutional network.Finally,an arithmetic analysis is carried out with a modified IEEE 33-node test system to verify the effectiveness of the proposed method and its advantages over other methods.The results show that the trained reinforce-ment learning agent based on graph convolutional networks exhibits better performance when the topology of the distribution network changes and the measurement data are lost.关键词
分布式光伏/配电网/电压无功优化/深度强化学习/图卷积网络Key words
distributed photovoltaics/distribution networks/voltage and reactive power optimization/deep reinforcement learning/graph convolutional networks分类
动力与电气工程引用本文复制引用
朱涛,海迪,李文云,黄伟,周胜超,吴明贺,王逸飞..基于图神经网络与强化学习的配电网电压与无功功率优化方法[J].南方电网技术,2024,18(11):67-78,12.基金项目
国家自然科学基金资助项目(52007032). Supported by the National Natural Science Foundation of China(52007032). （52007032）
