Renewable Energy Source Integration With Intelligent Neuro‐Fuzzy Control for Microgrid System

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Microgrids (MGs) are a solution to excessive load demand and power grid failure because they provide utility systems with stability and continuous power flow. A controller for a Fuzzy Logic System with neural network that is adaptable (Adaptive Fuzzy Neural Network Inference System) is suggested for a hybrid microgrid that is fueled by renewable energy sources. A modern high‐gain Landsman converter is one of the numerous converters in use is employed to increase the solar output and achieve a steady DC‐link voltage to provide outputs with high efficiency. The converter control is accomplished via the ANFIS method, a noteworthy substitute that combines two computational techniques: Neural networks and fuzzy set theory (ANN). Using the Crow Search Algorithm (CSA), the ANFIS constraints are reinforced to boost the convergence rate and dependability predictive accuracy rate. PWM‐based rectification system controlled by a Proportional‐integral control algorithm then links the wind system and microgrid configuration. When power from solar and wind sources is scarce, energy storage battery system (BESS) is used to hold energy for use in the DC connection. The MATLAB platform simulates evaluations of the control strategy. The proposed Landsman converter with high gain demonstrates superior energy efficiency compared to the Super Lift Luo converter, which in turn makes it a more effective solution for stabilizing DC‐link voltage and boosting RES outputs in hybrid microgrid systems.

This publication has 39 references indexed in Scilit: