Uncertainty-Aware Multi-Branch Graph Attention Network for Transient Stability Assessment of Power Systems Under Disturbances

With the rapid development of modern society and the continuous growth of electricity demand, the stability of power systems has become increasingly critical. In particular, Transient Stability Assessment (TSA) plays a vital role in ensuring the secure and reliable operation of power systems. Existing studies have employed Graph Attention Networks (GAT) to model both the topological structure and vertex attributes of power systems, achieving excellent results under ideal test environments. However, the continuous expansion of power systems and the large-scale integration of renewable energy sources have significantly increased system complexity, posing major challenges to TSA. Traditional methods often struggle to handle various disturbances. To address this issue, we propose a graph attention network framework with multi-branch feature aggregation. This framework constructs multiple GAT branches from different information sources and employs a learnable mask mechanism to enhance diversity among branches. In addition, this framework adopts an uncertainty-aware aggregation strategy to efficiently fuse the information from all branches. Extensive experiments conducted on the IEEE-39 bus and IEEE-118 bus systems demonstrate that our method consistently outperforms existing approaches under different disturbance scenarios, providing more accurate and reliable identification of potential instability risks.