Explainable Graph Neural Networks for Power Grid Fault Detection

This paper proposes the application of explanation methods to enhance the interpretability of graph neural network (GNN) models in fault location for power grids. GNN models have exhibited remarkable precision in utilizing phasor data from various locations around the grid and integrating the system’s topology, an advantage rarely harnessed by alternative machine learning techniques. This capability makes GNNs highly effective in identifying fault occurrences in power grids. Despite their greater performance, these models can encounter criticism for their "black box" nature, which conceals the reasoning behind their predictions. Lack of transparency significantly hinders power utility operations, as interpretability is crucial to building trust, accountability, and actionable insights. This research presents a comprehensive framework that systematically evaluates state-of-the-art explanation strategies, representing the first use of such a framework for Graph Neural Network models for defect location detection. By assessing the strengths and weaknesses of different explanatory methods, it identifies and recommends the most effective strategies for clarifying the decision-making processes of GNN models. These recommendations aim to improve the transparency of fault predictions, allowing utility providers to better understand and trust the models’ output. The proposed framework not only enhances the practical usability of GNN-based systems but also contributes to advancing their adoption in critical power grid applications.