采用RBF神经网络改进有限集模型预测控制算法的光伏系统MPPT研究  

Research on MPPT of Photovoltaic System by Using RBF Neural Network to Improve Finite Sets Model Predictive Control Algorithm

作　　者：王田宇 赵葵银[1] 曹哲 黄炜杰 林国汉[1] WANG Tianyu;ZHAO Kuiyin;CAO Zhe;HUANG Weijie;LIN Guohan(College of Electrical and Information Engineering,Hunan Institute of Engineering,Xiangtan 41l104,China)

机构地区：[1]湖南工程学院电气与信息工程学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2024年第2期7-13,共7页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省科技创新计划重点项目(2020RC5019)。

摘　　要：针对基于扰动观察法或电导增量法控制的光伏系统存在发电功率不稳定的问题,提出一种基于RBF神经网络改进的模型预测控制的最大功率点追踪算法,使用RBF神经网络拟合光伏系统功率-电压(P-V)曲线,预测光伏面板发电功率,通过建立光伏系统前级DC-DC变换器的数学模型,使用模型预测控制确保光伏面板工作在最大功率点提升光电转换效率.通过MATLAB/Simulink仿真结果表明,在外界环境快速变化的情况下,所提策略能有效抑制最大功率点漂移,提高系统光电转换效率.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.

关 键 词：光伏功率预测 RBF神经网络 有限集模型预测 

分 类 号：TM615.2[电气工程—电力系统及自动化]