MIMO Reinforcement Learning based Approach for Frequency Support in Microgrids with High Renewable Energy Penetration

Abstract

In this paper we propose here a nonlinear control scheme for frequency support in low-inertia microgrids with high level integration of renewable energy sources. We first develop a multi-loop reinforcement learning based controller with deep deterministic policy gradient optimization. Then, we apply it to the simultaneous frequency support and control of renewable energy generation. In addition, we adjust the reward system to track the thermal power and provide the balance between energy generation and consumption. This modified controller is shown to work well in several practical scenarios, in which it is compared to a single loop RL controller.