Application of BP Neural Network for Line Losses Calculation Based on Quantum Genetic Algorithm

摘要：

In order to improve the accuracy of line losses calculation, a novel calculation method based on the Quantum Genetic Algorithm and BP neural network has been proposed for line losses in this paper. BP neural network has been used as regression model in this paper, and the Quantum Genetic Algorithm has been used to search the weights matrix and thresholds of BP neural network. BP neural network could make prediction accurately for test lines, while fitting accurately the known results. The weaknesses of BP neural network, such as easy to trap in local minimum, low precision computing and poor generalization ability, could be overcome through the Quantum Genetic Algorithm searches the parameters of BP neural network. Finally the experiment results shows that compared with traditional methods, the calculation method based on the Quantum Genetic Algorithm and BP neural network has better performance in reducing the calculation errors.

关键词： component Line Losses Quantum Genetic Algorithm BP Neural Network Open Dataset Prediction Classifier Errors

作者: Kewen Liu Haiming Zhou Zhanyong Yang Fumin Qu

作者单位: China Electric Power Research Institute, Beijing, China

会议类型: 国际会议

会议名称: 2011 Fourth International Symposium on Computational Interlligence and Design 第四届计算智能与设计国际会议 ISCID 2011

会议地点: 杭州

会议语种:英文

页码: 3-7

在线出版日期: 2011-10-28（万方平台首次上网日期，不代表论文的发表时间）