Detection of FDIA in Power Grid Based on Hypergraph and Attention Mechanism

Abstract

False data injection attack (FDIA) is posing a threat to the security of power grids. Detection technology is an effective means to defend against FDIA, but the existing mainstream methods have insufficient detection capabilities for large-scale power grids. This study proposes a novel method that combines subgraph partitioning strategy and hypergraph model to detect FDIA. According to the principle the attack principle, the power grid is partitioned into subgraphs. Each subgraph is constructed as the hypergraph and then input into the hypergraph convolutional neural network (HGCNN). The hypergraph attention mechanism (HGAT) is adopted to pay attention to the hyperedge, where the attention score is calculated through the similarity between the node and the hyperedge. Simulations were conducted on IEEE 14-, 118-, and 300-bus systems. At the 10% attack intensity, the proposed method achieved 1.62%, 2.05%, and 2.18% higher accuracy than the optimal results of the comparison methods on three test systems, respectively.