摘要
配网运行维护费受到社会、经济、政策、资源等多种因素影响,且各因素的作用机理复杂,导致配网运行维护费与影响因素之间的关系很难用线性来表述。基于此建立一种将灰色关联度分析与人工神经网络相结合的配网运行维护费预测模型,通过灰色关联度分析提取影响配网运行维护费的主要因素作为人工神经网络模型的输入变量,采用浙江省相关数据进行实证,研究表明,灰色关联度分析方法有效减少了人工神经网络预测模型中的输入变量个数,并在一定程度上提高了人工神经网络配网运行维护费预测模型的预测精度。较之多元线性回归预测模型和人工神经网络预测模型,灰色关联度分析与人工神经网络相结合的配网运行维护费预测模型的预测性能有显著提高。
Operation and maintenance of electric distribution network is a critical component of the power grid enterprise investment.To optimizethe investment strategy,it is necessary to estimate the exact cost of network operation and maintenance.However,the estimation involves various potential impact factors,categories of which including social,economic,policy,resources,etc.Furthermore,the mechanism among those factors is so complicated that can be hardly described using linear models.Thevefore,a cost predictive model with the combination ofgrey relational analysis and artificial neural network is constructed.The main factors affecting theoperation and maintenance cost ofdistribution network are extracted by the grey relational analysis and are collected as the input variables of artificial neural network model.An empirical study is carried out on the relevant data of 19 country-level companies.The research shows that the grey relational analysis canefficiently reduce the number of input variables of artificial neural network prediction model,which subsequently improve the predicting accuracyof artificial neural network model.Compared with multiple linear regression prediction model and artificial neural network prediction model,the prediction performance of distribution network operation and maintenance cost prediction model is significantly improved by combining grey relational analysis and artificial neural network.
作者
陆晓芬
文凡
宋红芳
陈飞
魏聪
LU Xiao -fen;WEN Fan;SONG Hong- fang;CHENG Fei;WEI Cong(Zhejiang Electric Power Company, Hangzhou 310008, China;Zhejiang Huayun Information Technology Company, Hangzhou 310008,China;Zhejiang University of Finance and Economics, Hangzhou 310018,China)
出处
《经济问题》
CSSCI
北大核心
2018年第6期95-99,116,共6页
On Economic Problems
基金
国网浙江省电力公司科学技术项目(5211JY15001T)
关键词
运行维护费
影响因素
灰色关联度分析
人工神经网络
预测模型
operation and maintenance
influential factors
grey relational analysis
artificial neural network
prediction model