华南理工大学学报(自然科学版) ›› 2014, Vol. 42 ›› Issue (8): 39-44.doi: 10.3969/j.issn.1000-565X.2014.08.007

• 动力与电气工程 • 上一篇    下一篇

基于Odds-Matrix 算法的中长期电量组合预测方法及其应用

欧阳森 冯天瑞 李翔 王克英   

  1. 华南理工大学 电力学院,广东 广州 510640
  • 收稿日期:2013-11-14 修回日期:2014-05-08 出版日期:2014-08-25 发布日期:2014-07-01
  • 通信作者: 欧阳森(1974-),男,博士,副研究员,主要从事电能质量、节能技术与智能电器研究. E-mail:Ouyangs@scut.edu.cn
  • 作者简介:欧阳森(1974-),男,博士,副研究员,主要从事电能质量、节能技术与智能电器研究.
  • 基金资助:

    国家自然科学基金重点资助项目( 50937001) ; 华南理工大学中央高校基本科研业务费专项资金资助项目( 2012ZM0018)

Odds-Matrix Algorithm-Based Combination Forecasting Method of Medium and Long Term Electricity Consumption and Its Application

Ouyang Sen Feng Tian-rui Li Xiang Wang Ke-ying   

  1. School of Electric Power,South China University of Technology,Guangzhou 510640,Guangdong,China
  • Received:2013-11-14 Revised:2014-05-08 Online:2014-08-25 Published:2014-07-01
  • Contact: 欧阳森(1974-),男,博士,副研究员,主要从事电能质量、节能技术与智能电器研究. E-mail:Ouyangs@scut.edu.cn
  • About author:欧阳森(1974-),男,博士,副研究员,主要从事电能质量、节能技术与智能电器研究.
  • Supported by:

    国家自然科学基金重点资助项目( 50937001) ; 华南理工大学中央高校基本科研业务费专项资金资助项目( 2012ZM0018)

摘要: 中长期电量的组合预测存在权重选择困难,适应性、抗干扰性较差的问题. 文中结合目前广泛应用的组合预测技术,设计了以Odds-Matrix 算法为核心的Odds-Matrix 组合预测方法. 该组合预测方法利用Odds-Matrix 算法对单一预测模型的有效性进行定量分析,用权重概率分布函数来描述各个方法的优劣,然后根据权重进行单一预测模型的筛选和组合. 利用实际数据对所设计的Odds-Matrix 组合预测方法进行测试,结果表明,文中预测方法的精确度较其他常用组合预测法较高,说明该方法具有较强的适应性与抗干扰性.

关键词: 电量预测, Odds-Matrix 算法, 组合预测, 模型筛选

Abstract:

For the combination forecasting of the medium and long term electricity consumption,there exists a difficultyin selecting weights as well as the problems of poor adaptability and low noise immunity.Aiming at the aboveissues,an odds-matrix combination forecasting method based on the odds-matrix algorithm is proposed by taking intoaccount the widely-used combination forecasting technique.In this method,the odds-matrix algorithm is employedto carry out the quantitative analysis on the validity of single forecasting models,and the probability distributionfunction of the weight is adopted to describe the advantages and disadvantages of each method.Then,singleforecasting models are selected and combined based on the weight.Finally,the proposed method is tested by usingthe actual data.The results show that the proposed method achieves a higher accuracy in comparison with othercommonly-used combination forecasting methods,which means that it possesses stronger adaptability and betternoise immunity.

Key words: electric load forecasting, odds-matrix algorithm, combination forecasting, model selection

中图分类号: