Power System Short-Term Voltage Stability Assessment Method Based on Spatial-Temporal Graph Attention Network

Abstract

Short-term voltage stability (STVS) assessment is critical for ensuring the operational security of modern industrial internet-based power systems. For data-driven STVS evaluation approaches, effectively leveraging both time-series data and topological structure of complex industrial power networks to extract critical spatial-temporal features remains a challenge. This paper introduces a novel spatial-temporal feature learning framework, termed spatial-temporal graph attention network (STGAT), which integrates graph attention network (GAT) and bidirectional gated recurrent unit (BiGRU). In the framework, channel attention mechanism (CAM) is incorporated into the GAT to enhance spatial representation, while temporal attention mechanism is applied to the BiGRU to capture essential temporal features. By considering highly representative spatial-temporal correlations of power system dynamics, the recommended STGAT model delivers a fast, accurate, and robust classification framework for STVS assessment. Extensive testing on the IEEE 39-bus system validates the feasibility and preeminence of the recommended STGAT method compared to existing models, ensuring its suitability for online STVS assessment in industrial environments.