Reinforcement Learning for Centralized Fault Coordination in Power Systems

In this project, we develop a hybrid reinforcement learning framework for adaptive protection in power grids with high DER penetration. A centralized model is first trained using system-wide current, voltage, and impedance data to coordinate both primary and backup relays, followed by decentralized fine-tuning using only local measurements to ensure autonomous operation in case of communication loss. The approach aims to improve relay coordination, robustness, and decision-making by exploring different recurrent network architectures such as RNN and LSTM.