Damping inter?area oscillation using reinforcement learning controlled TCSC

Inter-area oscillation is a serious problem that threatens power system. Appropriate damping control of the inter-area would ensure grid stability and maintain tie-line transfer capability. In this paper, novel reinforcement learning (RL) based (POD) controller proposed uses Thyristor Controlled Series Compensators (TCSC) to damp oscillations. By leveraging unbiased gradient direction estimation natural evolution strategy (NES), flows on tie-lines were successfully regulated oscillations damped through dynamically modulating inserted reactance TCSC. Furthermore, parallel computation techniques adopted speed up training process NES. The RL-based POD has been tested both two-area four-machine system North American MinniWECC Extensive studies have demonstrated excellent performance TCSC in