Adaptive Predictive Control with Neuro-Fuzzy Parameter Estimation for Microgrid Grid-Forming Converters

Model predictive control (MPC) is a flexible and multivariable technique with better dynamic performance than linear control. However, MPC sensitive to parametric mismatches that reduce its capabilities. In this paper, we present new method of improving the robustness filter parameter variations/mismatches by easily implementable estimation. Furthermore, extend proposed for wider operating conditions novel neuro-fuzzy The results, which are demonstrated both simulations real-time hardware-in-the-loop tests, show steady-state estimation accuracy 95%, at least 20% improvement in total harmonic distortion (THD) conventional non-adaptive under up 50% nominal values.