可再生能源2018，Vol.36Issue(5)：701-706,6.
基于遗传算法及BP神经网络的混合孤岛检测方法
A hybrid islanding detection method based on genetic algorithm and BP neural network
摘要
Abstract
Photovoltaic islanding detection is a hot research topic in the field of photovoltaic technology in recent years.Firstly,the islanding detection method based on BP neural network was introduced.The theoretical and experimental results show that this method has low accuracy and high misjudgment rate. A hybrid islanding detection method based on genetic algorithm and BP neural network was proposed,which was based on genetic algorithm to optimize the initial threshold value and weight value of BP neural network and was applied to achieve the island detection.It can effectively alleviate the disadvantage of locally optimum of BP neural network. Through the analysis of its mechanism and the experimental results in matlab/simulink,this method has a smaller none detection zone (NDZ).It will not affect the power quality of the system.The detection speed is faster,and the misjudgment rate is low. The algorithm is analyzed on DSP. The experimental results verify the correctness and effectiveness of the proposed method.关键词
BP神经网络/遗传算法/混合孤岛检测方法/检测盲区Key words
BP neural network/genetic algorithm/hybrid islanding detection method/NDZ分类
能源科技引用本文复制引用
余运俊,衷国瑛,万晓凤,辛建波,夏永洪..基于遗传算法及BP神经网络的混合孤岛检测方法[J].可再生能源,2018,36(5):701-706,6.基金项目
国家自然科学基金(61563034) （61563034）
国家国际科技合作专项(2014DFG72240) （2014DFG72240）
江西省自然科学基金(20151BAB206051). （20151BAB206051）
