A Heterogeneous Graph-Based Multi-Task Learning for Fault Event Diagnosis in Smart Grid

TL;DR

This paper introduces a heterogeneous multi-task learning graph neural network for fault diagnosis in smart grids, capable of detecting, locating, classifying faults, and estimating fault parameters, validated on IEEE test systems.

Contribution

It presents a novel GNN-based multi-task framework for comprehensive fault diagnosis and a new explainability method for identifying key nodes in the distribution system.

Findings

High accuracy in fault detection, location, and classification.

Effective fault resistance and current estimation.

Robust performance demonstrated on IEEE-123 test feeder.

Abstract

Precise and timely fault diagnosis is a prerequisite for a distribution system to ensure minimum downtime and maintain reliable operation. This necessitates access to a comprehensive procedure that can provide the grid operators with insightful information in the case of a fault event. In this paper, we propose a heterogeneous multi-task learning graph neural network (MTL-GNN) capable of detecting, locating and classifying faults in addition to providing an estimate of the fault resistance and current. Using a graph neural network (GNN) allows for learning the topological representation of the distribution system as well as feature learning through a message-passing scheme. We investigate the robustness of our proposed model using the IEEE-123 test feeder system. This work also proposes a novel GNN-based explainability method to identify key nodes in the distribution system which then facilitates informed sparse measurements. Numerical tests validate the performance of the model across all tasks.