[1]袁秀芳,张征,郑伯川,等.基于SVR的多变量电力消费预测[J].西华师范大学学报(自然科学版),2015,36(03):289-294.
 YUAN Xiu fang,ZHANG Zheng,ZHENG Bo chuan,et al.Prediction for Multivariable Electricity Consumption Based on SVR[J].Journal of China West Normal University(Natural Sciences),2015,36(03):289-294.
点击复制

基于SVR的多变量电力消费预测()
分享到:

《西华师范大学学报(自然科学版)》[ISSN:1673-5072/CN:51-1699/N]

卷:
36
期数:
2015年03期
页码:
289-294
栏目:
出版日期:
2015-09-20

文章信息/Info

Title:
Prediction for Multivariable Electricity Consumption Based on SVR
作者:
袁秀芳张征郑伯川焦伟超
西华师范大学 数学与信息学院,四川 南充637009
Author(s):
YUAN XiufangZHANG ZhengZHENG BochuanJIAO Weichao
College of Mathematic and information, China west normal university,Nanchong Sichuan 637009,China
关键词:
支持向量机电力消费预测支持向量回归机
Keywords:
support vector machines electricity consumption predictingsupport vector regression
分类号:
O29
文献标志码:
A
摘要:
电力消费受多种因素的影响,揭示因素与电力消费的关系是当前电力消费研究的一个重要内容.应用支持向量回归机模型,利用年电力消费、人均国内生产总值、重工业比重以及电能效率的数据,分别对电力消费进行双变量和多变量的支持向量回归机预测.实验对比分析两种方式下预测值与真实值差异情况,说明了多变量方式下支持向量回归机的预测值与真实值更一致.
Abstract:
Electricity consumption is affected by many factors, and the relationship between the factors and the electricity consumption has become one of important study contents of the electricity consumption. In this paper, the support vector regression model is used to predict the electricity consumption by two ways of bivariate and multivariate regression separately. Adopted data includes the electricity consumption per year, the per capita gross domestic product, the proportion of heavy industry and the energy efficiency. The difference between predicted values and actual values, which are obtained in two ways, is compared and analyzed by experiments. The experimental results show that the predicted value and the actual value obtained in the way of multivariate regression are more consistent than the other way.

参考文献/References:

[1]伏进.重庆市电力消费与经济增长的关系分析及电力产业政策建议[D].重庆大学,2008.
[2]董智,程春萌.河南省电力消费弹性系数变动状况分析[J].电力系统保护与控制,2010,38(5):60-63.
[3]左金金.北京市电力消费与经济增长的动态关系研究[D].北京工业大学,2013.
[4]陈万林.江苏省电力消费分析及预测研究[D].南京财经大学,2012.
[5]邓鸿鹄.北京市能源消费预测方法比较研究[D].北京林业大学,2013.
[6]VAPNIK V, GOLOWISH S, SMOLA A. Support Vector Method for Function Approximation, Regression Estimation, and Signal Processing[M]. Cambridge, MA, MIT Press, 1997, 281-287.
[7]杨建辉,李龙.基于SVR的期权价格预测模型[J].系统工程理论与实践,2011,31(5):848-854.
[8]辛霄.基于贝叶斯支持向量机的粮食产量预测的研究[D].首都师范大学,2012.
[9]WU C H, HO J M, LEE D T. TravelTime Prediction With Support Vector Regression[J]. IEEE Transactions on intelligent Transportation Systems, 2004, 5(4):276-281.
[10]张彦周,贾利新.基于网格寻优SVR房价预测模型—以郑州市为例[J].河南科学,2014,32(8):1659-1663.
[11]MOHSEN B, KEYVAN A, MORTEZA E, et al.Generalization Performance of Support Vector Machines and Neural Networks in Runoff Modeling[J].Expert Systems with Applications,2009, 36(4):7624-7629.
[12]CHANG C C, LIN C J. LIBSVM:a Library for Support Vector Machines[EB/OL][2015-01-08].http://www.csie.edu.tw/~cjlin/libsvm/.

相似文献/References:

[1]焦伟超,郑伯川,袁秀芳.一种基于SVM的真伪车牌分类算法[J].西华师范大学学报(自然科学版),2016,37(02):233.[doi:10.16246/j.issn.1673-5072.2016.02.022]
 JIAO Weichao,ZHENG Bochuan,YUAN Xiufang.An Algorithm Based on SVM to Classify True or False License Plates[J].Journal of China West Normal University(Natural Sciences),2016,37(03):233.[doi:10.16246/j.issn.1673-5072.2016.02.022]
[2]张文军,张运陶.基于支持向量机的苯酚类化合物毒性的QSAR研究[J].西华师范大学学报(自然科学版),2008,29(02):186.[doi:10.16246/j.issn.1673-5072.2008.02.013]
 ZHANGWen-jun,ZHANGYun-tao.QSARStudyonPhenolDerivativesToxicity BasedonSupportVectorMachine[J].Journal of China West Normal University(Natural Sciences),2008,29(03):186.[doi:10.16246/j.issn.1673-5072.2008.02.013]
[3]王晓慧,李云飞.基于支持向量机的个人信用风险评价研究[J].西华师范大学学报(自然科学版),2017,38(02):195.[doi:DOI:10.16246/j.issn.1673-5072.2017.02.015]
 WANG Xiaohui,LI Yunfei.Personal Credit Risk Assessment Based on Support Vector Machine (SVM)[J].Journal of China West Normal University(Natural Sciences),2017,38(03):195.[doi:DOI:10.16246/j.issn.1673-5072.2017.02.015]

备注/Memo

备注/Memo:
收稿日期:2015-01-08
基金项目:四川省教育厅自然科学重点项目(12ZA172);西华师范大学启动基金(12B023).
作者简介:袁秀芳(1990-),女,陕西延安人,西华师范大学数学与信息学院硕士研究生,主要从事统计回归分析和支持向量机研究.
通讯作者:郑伯川(1974-),男,四川自贡人,西华师范大学数学与信息学院教授,博士,主要从事人工神经网络、机器学习、图像图形研究.Email:zhengbochuan@126.com
更新日期/Last Update: 2015-09-20