Intelligent RBF neural network-based control for dynamic stability and power control in renewable-integrated microgrids

Managing and controlling energy in microgrids is a difficult task because of AC and DC components operate differently, causing frequency and voltage problems. The control and process of microgrids in the occurrence of Hybrid Renewable Energy Sources (HRES) are developed in this research. The Radial Basis Function Neural Network (RBFNN) controller provides real-time monitoring, optimization and control through communication and data acquisition modules. The power conversion process features a Z-source integrated coupled inductor boost (Z-SCIB) converter for the Photovoltaic (PV) system, which is controlled by Grey Lag Goose Optimization (GGO) based Proportional-Integral (PI) controller. The Doubly Fed Induction Generator (DFIG)-Wind Energy Conversion System (WECS) output is rectified using a Pulse Width Modulation (PWM) rectifier that is managed by a PI controller to sustain optimal power transfer and stability. A Bidirectional converter is exploited to incorporate the battery storage system into the DC link, allowing effective charge and discharge cycles in accordance to the power demand and generation within the microgrid. The DC link, which acts as the common power bus for the microgrid, is interfaced with the grid. Significant enhancements in system performance, stability and control accuracy are shown by extensive simulations conducted in MATLAB/Simulink tool under a variety of operating conditions with converter efficacy of[Formula: see text].