Causality and Interpretability for Electrical Distribution System faults

TL;DR

This paper introduces a novel method combining causal inference and machine learning with graph models to accurately classify electrical faults and interpret their root causes, enhancing system reliability.

Contribution

It presents a new approach that integrates causal graph construction with graph neural networks and interpretability techniques for fault classification in electrical systems.

Findings

Achieved 99.44% accuracy on fault classification dataset.

Enhanced interpretability of fault causes using GNNExplainer and Captum.

Outperformed existing state-of-the-art models in fault detection.

Abstract

Causal analysis helps us understand variables that are responsible for system failures. This improves fault detection and makes system more reliable. In this work, we present a new method that combines causal inference with machine learning to classify faults in electrical distribution systems (EDS) using graph-based models. We first build causal graphs using transfer entropy (TE). Each fault case is represented as a graph, where the nodes are features such as voltage and current, and the edges demonstrate how these features influence each other. Then, the graphs are classified using machine learning and GraphSAGE where the model learns from both the node values and the structure of the graph to predict the type of fault. To make the predictions understandable, we further developed an integrated approach using GNNExplainer and Captums Integrated Gradients to highlight the nodes (features) that influences the most on the final prediction. This gives us clear insights into the possible causes of the fault. Our experiments show high accuracy: 99.44% on the EDS fault dataset, which is better than state of art models. By combining causal graphs with machine learning, our method not only predicts faults accurately but also helps understand their root causes. This makes it a strong and practical tool for improving system reliability.