Damping enhancement in the presence of load parameters uncertainty using reinforcement learning based SVC controller

This paper proposes a reinforcement learning based SVC controller to improve the damping of power systems in the presence of load model parameters uncertainty. The proposed method is trained over a wide range of typical load parameters in order to adapt the gains of the SVC stabilizer. The simulation results show that the tuned gains of the SVC stabilizer using reinforcement learning can provide better damping than the conventional fixed-gains SVC stabilizer. To evaluate the usefulness of the proposed method, we compare the response of the proposed method with PD controller. The simulation results show that our method has the better control performance than PD controller.