1改进的F-score特征选择算法-电测与仪表.docVIP

第44卷 第504期 电测与仪表 Vol.44 No.504 2007年 第12期 Electrical Measurement Instrumentation Dec.2007 PAGE 1 - 改进F-score特征选择的MPSO-BP神经网络短期负荷预测* 丁坚勇1，朱炳翔1，田世明2，卜凡鹏2，陈俊艺1，朱天曈1 （1. 武汉大学 电气工程学院，武汉 430072；2. 中国电力科学研究院，北京 100192） 摘要：本文针对海量数据提出一种基于改进Fisher分数（F-score）特征选择的改进粒子群优化的BP (modified particle swarm optimization and back propa- gation, MPSO-BP)神经网络短期负荷预测方法。首先采用改进F- score特征评价准则计算影响负荷预测精度各个特征的F-score值，再通过F-score Area法设定阈值筛选出最优特征子集，然后将最优特征子集作为MPSO -BP神经网络模型的输入变量完成对预测日一天24点负荷的预测，并与MPSO -BP神经网络短期负荷预测和传统BP神经网络短期负荷预测进行对比。算例表明，本文提出的短期负荷预测方法可以较好地对海量数据进行挖掘，具有较高的预测精度。 关键词：F-score特征选择；降维；最优特征子集；改进粒子群 中图分类号：TM933 文献标识码：B 文章编号：1001-1390（2015）00-0000-00 Short Short-term load forecasting of MPSO-BP neural network improved by particle swarm optimization based on improved F-score feature selection Ding JianYong1,Zhu BingXiang1, Tian ShiMing2,Bo FanPeng2,Chen JunYi1 (1. School of Electrical Engineering, Wuhan University, Wuhan 430072, Hubei Province, China. 2. China Electric Power Research Institute, Haidian District, Beijing 100192, China.) Abstract： : In this paper, a short-term load forecasting method of MPSO-BPBP (modified particle swarm optimization and back propagation) neural network based on improved F-score feature selection?is proposed for mass data... Firstly, the improved F-score feature evaluation criterion is used to calculate the F-score value of each feature affecting the load forecasting accuracy, Thenthen, the optimal feature subset was selected by the F –- score Area area method，.By using the optimal feature subset as input variable of the MPSO-BP neural network model to complete tThe forecast of 24 24-point load is completed by using the optimal feature subset as input variable of the MPSO-BP neural network model, as well as comparing with the short-term load forecasting of MPSO-BP neural network and he traditional BP neural ne