A New Reinforcement Learning Based Voltage Control for Three-Phase AC/DC Converter

This paper proposes a novel integral reinforcement learning (IRL) based DC-link voltage control method for three-phase AC/DC converter. The proposed IRL control autonomously updates the optimal control gains using online data trained neural network. It produces superior control performance without the knowledge of system model parameters. Compared with the existing control approaches for three-phase AC/DC converter, it offers the benefits of model independence and autonomous gain tuning. The effectiveness of the proposed IRL method is verified by simulation results.