Power System Transient Stability Assessment Based on Graph Neural Network with Interpretable Attribution Analysis

Abstract

The power transient stability analysis is one of the basis for determining the control strategy of power system security and stability. Considering the influence of power grid topology on the transient stability of power system, the transient stability evaluation model is constructed based on the graph attention neural network. The electrical components and their transient operation data are mapped to the graph data with the spatial topology characteristics of power system for model training, so as to improve the topological generalization performance of the model. The marginal contribution of input characteristics to the output of transient power angle stability evaluation model is quantitatively calculated based on Shapley additive explanation (SHAP), so as to improve the interpretability of data-driven method for transient power angle stability evaluation. The effectiveness of the proposed method is verified by the IEEE 39-bus system.