The Research on Chain Fault Prediction in AC-DC Hybrid Power Grids Based on Deep Learning

Accurate prediction of cascading faults in power grids is critical for ensuring their stability and preventing large-scale outages. This paper presents Hybrid Graph-Temporal Transformer (HGTT), for predicting cascading faults in AC/DC hybrid power grids. The HGTT model integrates Graph Attention Networks (GAT) and Temporal Transformers, effectively capturing both spatial and temporal dependencies. Key innovations include an attention mechanism that accounts for electrical distances between nodes, and a causal attention-based temporal feature extraction module. Additionally, two self-supervised tasks reduce reliance on labeled data. Experimental results show that HGTT improves prediction accuracy by over 15% and reduces labeled data requirements by 50%.