An Advanced Learning-Based Linear Quadratic Regulator For Proton Exchange Membrane Fuel Cell in DC Microgrids

An advanced learning-based linear quadratic regulator (LQR) is proposed to enhance the output voltage control performance of proton exchange membrane fuel cell (PEMFC) in DC microgrids. Compared with the commonly used methods, such as the PI control and model predictive control (MPC). The proposed control method not only produces better tracking performances, but also overcomes the problem of model dependence. The superiority of proposed method under system parameter variations is verified by simulation results.