摘要详情

ID / 提交时间

128 / 2023-10-18 16:05:25

标题

Research on vulnerability assessment method of electric power network based on graph neural

关键字

Graph neural network; Complex network; Eigenvector Centrality;

主题及专题

3.Power system and automation > (1) Modeling, control and stability analysis in power system

状态

全文录用

作者

Zijian Wan / Southwest Jiaotong University

Xu Liu / Southwest Jiaotong University

Yeqing Zhang / Southwest Jiaotong University

Yan Wang / Southwest Jiaotong University

Yida Zeng / Southwest Jiaotong University

摘要

This paper proposes a vulnerability assessment method for power network based on graph neural network using complex network theory and graph neural network model. First, the eigenvector centrality (EC) in complex network theory is chosen as the measure of power system vulnerability. Second, an unsupervised power network vulnerability assessment model based on graph neural networks is established based on power system topological parameters and operational data. Finally, the learning effect and computational time efficiency of the model are explored, and the key nodes in the power network are identified.