Research on MPPT of Photovoltaic System by Using RBF Neural Network to Improve Finite Sets Model Predictive Control Algorithm
When the solar irradiance continues to change,the photovoltaic system based on the perturbation observation method or the conductance increment method has the problem of unstable power generation.This paper proposes a maximum power point tracking algorithm based on RBF neural network improved model predictive control(referred to as the improved model predictive control MPPT method).The RBF neural net-work is used to fit the power-voltage(P-V)curve of the photovoltaic system to predict the power generation of the photovoltaic panel.By establishing the mathematical model of the front-stage DC-DC converter of the pho-tovoltaic system,the model predictive control is used to ensure that the photovoltaic panel works at the maxi-mum power point and improves the photoelectric conversion efficiency.Through MATLAB/Simulink simula-tion,it is shown that the proposed strategy can effectively suppress the maximum power point drift and im-prove the photoelectric conversion efficiency of the system in the case of rapid changes in the external envi-ronment.
NETL
NSTL
万方数据
