A Novel Proportion-Integral-Differential Controller Based on Deep Reinforcement Learning for DC/DC Power Buck Converters

Abstract

The development of DC microgrids poses challenges to the stability and transient performance of DC/DC converters. This article proposes a controller for Buck converters based on reinforcement learning without theoretical model analysis. The proposed controller uses the deep deterministic policy gradient algorithm, and has good transient performance and robustness for load fluctuation when combined with the basic proportion-integral-differential controller applied in the Buck converter.