Enhanced Microgrid Performance Using Coupled Inductor Switched Z-Source Boost Converter and GOA-Tuned RBFNN MPPT

Microgrids are become increasingly prevalent in the near future because it serves a crucial purpose in incorporating
Distributed Renewable Energy Resources (DRES) into the main grid. Because green power sources including Photovoltaic (PV) energy are weather sensitive, they are inclined to be exceedingly fluctuating. These resources, when combined with demand, might cause unsystematic disparities on both load and generation sides, necessitating the implementation of an efficient control strategy to ensure a consistent power supply to grid. Consequently, this research proposes a robust optimized Maximum Power Point Tracking (MPPT) based control approach with dc to dc converter for delivering the high stability with constant power supply to the microgrid. At the PV side, a Coupled Inductor Switched Z-Source Boost (CISZB) converter is deployed to assure constant current functioning via mode of microgrid linked inverter. The incorporation of Artificial Intelligence (AI) control
methods for effective energy extraction improves the effectiveness of solar energy systems. As a result, a Grasshopper Optimisation Algorithm-based Radial Basis Function Neural Network (GOA-RBFNN) MPPT is presented to successfully extract the MPP in a PV array. Furthermore, this MPPT controller forecasts the duty factor of a CISZSB converter for the purpose of attaining the maximum power point. MATLAB/SIMULINK platform is utilized to simulate microgrid connected PV systems and functionality of the proposed system is determined with regard to MPP efficiency, and current Total Harmonic Distortion (THD).