Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters

An accurate definition of a system model significantly affects the performance model-based control strategies, for example, predictive (MPC). In this paper, model-free strategy is presented to mitigate all ramifications model’s uncertainties and parameter mismatch between plant controller power electronic converters in applications such as microgrids. A specific recurrent neural network structure called state-space (ssNN) proposed current three-phase converter. approach, NN weights are updated through particle swarm optimization (PSO) faster convergence. After training process, ssNN-PSO combined with using criterion overcomes variations physical system. comparison has been carried out conventional MPC different scenarios. The simulation results scheme exhibit more robustness compared finite-control-set MPC.