2020/01/30 by Yu-Xiao Liu, Liu, Yuxiao, Ning Zhang +9
Computer Science · #Anomaly Detection Techniques and Applications #FOS: Electrical engineering #Machine Learning and Data Classification #Signal Processing (eess.SP) #Software System Performance and Reliability #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2001.11553
openalex publication_date 2020/01/30 · openalex created_date 2020/02/07 · openalex updated_date 2026/07/28
Power system cascading failures become more time variant and complex because of the increasing network interconnection and higher renewable energy penetration. High computational cost is the main obstacle for a more frequent online cascading failure search, which is essential to improve system security. In this work, we show that the complex mechanism of cascading failures can be well captured by training a graph convolutional network (GCN) offline. Subsequently, the search of cascading failures can be significantly accelerated with the aid of the trained GCN model. We link the power network topology with the structure of the GCN, yielding a smaller parameter space to learn the complex mechanism. We further enable the interpretability of the GCN model by a layer-wise relevance propagation (LRP) algorithm. The proposed method is tested on both the IEEE RTS-79 test system and China's Henan Province power system. The results show that the GCN guided method can not only accelerate the search of cascading failures, but also reveal the reasons for predicting the potential cascading failures.