RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors (Papers Track)

Anmol Dwivedi (RPI); Ali Tajer (RPI); Santiago Paternain (Rensselaer Polytechnic Institute); Nurali Virani (GE Research)

Paper PDF NeurIPS 2024 Recorded Talk Cite
Power & Energy Hybrid Physical Models Reinforcement Learning

Abstract

Electricity grid's resiliency and climate change strongly impact one another due to an array of technical and policy-related decisions that impact both. This paper introduces a physics-informed machine learning-based framework to enhance grid's resiliency. Specifically, when encountering disruptive events, this paper designs remedial control actions to prevent blackouts. The proposed~\textbf{P}hysics-\textbf{G}uided \textbf{R}einforcement \textbf{L}earning (PG-RL) framework determines effective real-time remedial line-switching actions, considering their impact on power balance, system security, and grid reliability. To identify an effective blackout mitigation policy, PG-RL leverages power-flow sensitivity factors to guide the RL exploration during agent training. Comprehensive evaluations using the Grid2Op platform demonstrate that incorporating physical signals into RL significantly improves resource utilization within electric grids and achieves better blackout mitigation policies -- both of which are critical in addressing climate change.