Fault Detection for agents on power grid topology optimization: A Comprehensive analysis

TL;DR

This paper analyzes failures in power grid topology optimization using DRL agents, identifying failure patterns, and developing a predictive model that accurately forecasts grid failures with feature importance insights.

Contribution

It introduces a comprehensive failure detection and prediction framework for DRL-based power grid agents, including clustering of failure types and a high-performing failure prediction model.

Findings

Five distinct failure clusters identified in grid simulations.

LightGBM achieves 82% accuracy in failure prediction.

87% accuracy in classifying grid survival or failure.

Abstract

Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic grid scenarios and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed scenarios of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure prediction performance, with an accuracy of 82%. It also accurately classifies whether a the grid survives or fails in 87% of cases. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.