MoE-GraphSAGE-Based Integrated Evaluation of Transient Rotor Angle and Voltage Stability in Power Systems

The integration of renewable energy and power electronic devices has significantly complicated power system stability, making transient stability assessments increasingly challenging. In response, a recent paper presents MoE-GraphSAGE, a graph neural network framework that unifies the assessment of transient rotor angle stability (TAS) and voltage stability (TVS). By leveraging GraphSAGE's ability to capture the spatiotemporal features of power grids and employing a multi-expert network with a gating mechanism, MoE-GraphSAGE effectively models various instability modes. Experimental results on the IEEE 39-bus system indicate that this framework not only enhances accuracy but also improves computational efficiency, marking a significant advancement in online multi-task transient stability assessment in complex power systems.