摘要
高级量测体系的建设和深度学习技术的快速发展使得不依赖于物理模型,而是通过挖掘历史数据和先验知识快速地找到最佳无功优化策略成为了可能。为此,提出了一种基于图卷积网络(graph convolutional network,GCN)的配电网无功优化方法。通过邻接矩阵来表征配电网节点间的拓扑信息,所提出的算法能够有效地挖掘节点负荷之间的相关性,并利用深层图卷积架构映射电力设备状态与负荷数据之间复杂的非线性关系。仿真结果表明,GCN的无功优化精度和鲁棒性皆优于卷积神经网络、多层感知机和案例推理等现有的数据驱动方法,且求解时间远低于传统的启发式算法,可以满足配电网无功优化实时性的需求。
The construction of advanced metering infrastructure and the rapid development of deep learning technology make it possible to quickly find the optimal strategy for reactive power optimization by mining historical data and prior knowledge instead of relying on physical models.Therefore,a method for reactive power optimization based on graph convolutional network(GCN)is proposed.Through representing the topology information between nodes in distribution network with the adjacency matrix,the proposed algorithm can effectively mine the correlation between the node loads,mapping the complex nonlinear relationship between the power equipment status and the load data with the deep graph convolutional architecture.The simulation results show that the accuracy and robustness of the GCN are better than that of the existing data-driven methods such as the convolutional neural network,the multi-layer perceptron and the case-based reasoning.Its solution time is much shorter than the traditional heuristic algorithm,which can meet the real-time demand of the reactive power optimization in distribution networks.
作者
廖文龙
于贇
王煜森
陈洁婧
LIAO Wenlong;YU Yun;WANG Yusen;CHEN Jiejing(Department of Energy Technology,Aalborg University,Aalborg 9220,Denmark;School of Electrical Engineering and Computer Science,KTH Royal Institute of Technology,Stockholm SE-10044,Sweden;School of Software and Microelectronics,Peking University,Haidian District,Beijing 102600,China)
出处
《电网技术》
EI
CSCD
北大核心
2021年第6期2150-2160,共11页
Power System Technology
基金
国家留学基金项目的资助
关键词
配电网
无功优化
图卷积网络
深度学习
数据驱动
distribution network
reactive power optimization
graph convolutional network
deep learning
data driven