Optimal Transmission Switching for Short-Circuit Current Limitation Based on Deep Reinforcement Learning

The gradual expansion of power transmission networks leads to an increase in short-circuit current (SCC), which has impact on the secure operation when SCC exceeds interrupting capacity circuit breakers. In this regard, optimal switching (OTS) is proposed reduce while maximizing loadability with respect voltage stability. However, OTS model a complex combinatorial optimization problem binary decision variables. To address problem, paper employs deep Q-network (DQN)-based RL algorithm solve problem. Case studies IEEE 30-bus system and 118-bus are presented demonstrate effectiveness method. numerical results show that DQN-based agent can select effective branches at each step after implementing strategies.