In order to calculate the distribution line loss more accurately,a distribution line loss calculation model based on ge-netic algorithm(GA)and back propagation(BP)neural network is proposed.Using the daily power consumption and the monthly power consumption as the original data,the normalization and principal component analysis(PCA)methods are used to reduce the dimension of the daily power consumption and the monthly power consumption respectively.The parameters of BP neural network are optimized by GA,and the loss calculation of distribution line is realized by using the trained BP neural network.The experimental analysis of 217 distribution lines in a certain area shows that the accuracy of the proposed hybrid method(GA&BP)is better than other line loss calculation methods.
关键词
线损/特征提取/BP神经网络/遗传算法/主成分分析
Key words
line loss/feature extraction/BP neural network/genetic algorithm/principal component analysis
维普
万方数据