A Review of Graph Neural Networks and Their Applications in Power Systems

Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data these are typically represented Euclidean domains. Nevertheless, there is an increasing number of applications where collected non-Euclidean domains and as graph-structured with high-dimensional features interdependency among nodes. complexity has brought significant challenges the existing deep defined Recently, publications generalizing for systems emerged. In this paper, a comprehensive overview graph (GNNs) proposed. Specifically, several classical paradigms GNN structures, e. g., convolutional networks, summarized. Key such fault scenario application, time-series prediction, flow calculation, generation reviewed detail. Further-more, main issues some research trends about GNNs discussed.