Dynamic modeling of grid-connected photovoltaic system using artificial neural network and genetic algorithm

Abstract

Photovoltaic (PV) systems have one of the highest potentials and operating ways for generating electrical power by converting solar irradiation directly into the electrical energy. The aim of this study is to simulate and control of a grid-connected PV source using artificial neural network (ANN) and genetic algorithm (GA) controller. Also, for tracking the maximum power point (MPP), ANN and GA are used. Data are optimized by GA and then these optimized data are applied in the neural network training. The simulation results are presented by using Matlab/Simulink and show that the ANN-GA controller can meet the need of the load easily and have less fluctuations around the maximum power point (MPP), also it can increase convergence speed to achieve the MPP. Moreover, to control both line voltage and current, a grid side P-Q controller has been applied.