Fault Detection for agents on power grid topology optimization: A Comprehensive analysis
This work addresses the need for better fault detection in power grid optimization for researchers and practitioners using DRL agents, though it is incremental as it builds on existing environments and methods.
The paper tackled the problem of unclear failure causes in deep reinforcement learning agents for power grid topology optimization by analyzing failed scenarios to detect patterns and predict failures in advance. It identified five distinct failure clusters and achieved an 82% accuracy in failure prediction using a LightGBM model, with 87% accuracy in classifying grid survival or failure.
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.