基于灰色模型与神经网络组合的线损率预测  

Line Loss Rate Forecasting Based on Combination of Grey Model and Neural Network

作　　者：张勤[1] 周步祥[1] 林楠[2] 聂雅卓[1] 

机构地区：[1]四川大学电气信息学院,成都610065 [2]四川电力职业技术学院,成都610071

出　　处：《电力系统及其自动化学报》2013年第5期162-166,共5页Proceedings of the CSU-EPSA

摘　　要：对线损率预测的方法进行了研究,采用灰色模型与神经网络组合的方法对线损率进行预测。首先用GM(1,1)建模对线损率的变化趋势分析计算,运用灰色关联度分析与线损率相关的因素,确定出神经网络的输入变量,建立线损率预测的3层BP网络模型;然后采用GM(1,1)和神经网络的组合预测模型得到线损率的最终预测结果;最后通过对实例的分析,证明所提方法提高了线损率预测的精度。The paper is mainly focusing on the research of the method for line loss rate forecasting by adopting grey model combined with neural network. Firstly, GM （ 1,1 ） model can be used to analyze and calculate thevariation trend of line loss rate. The input variables of the neural network can be determined by the grey relationship of related factors. Three-layer BP model for line loss rate forecasting is constructed, and then the eventual result can be obtained by us- ing the combined model of GM （ 1,1 ） and neural network. Finally, an example is taken to prove the precision of line loss rate forecasting by the proposed method in the paper.

关 键 词：线损率 预测 灰色模型 神经网络 组合模型 

分 类 号：TM744[电气工程—电力系统及自动化]