Design of a Resistive Brake Controller for Power System Stability Enhancement Using Reinforcement Learning

摘要

Computation of the closed-loop control laws, capableto realize multiple switching operations of a resistive brake (RB)aimed to enhance power system stability, is the primary topicof this brief. The problem is formulated as a multistage decisionproblem and use of a model-based reinforcement learning(RL) method, known as prioritized sweeping, to compute thecontrol law is considered. To illustrate the performances of theproposed approach results obtained using the model of a syntheticfour-machine power system are given. Handling measurementtransmission delays is discussed and illustrated.