• HOME
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • Chinese
Site search        
文章摘要
基于混沌理论和Legendre正交基神经网络的短期负荷预测
Short-term Load Forecasting Based on Chaos Theory and Legendre Orthogonal Basis Neural Network
Received:June 28, 2014  Revised:August 18, 2014
DOI:
中文关键词: 混沌理论  Legendre  神经网络  衍生算法  短期负荷预测
英文关键词: chaos theory, Legendre  neural network, derivative algorithm, short-term load forecasting
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
Author NameAffiliationE-mail
YANG Hu-ping School of Information Engineering,Nanchang University yhping123@163.com 
ZUO Shi-wei* School of Information Engineering,Nanchang University zuoshuai9618@qq.com 
tuyuxi Nan chang University  
WANG Cheng-fei State Grid Ganxi Power Supply Company  
Hits: 1338
Download times: 777
中文摘要:
      考虑到短期负荷所具有的混沌特性和神经网络的非线性映射能力,本文提出了一种基于混沌理论的Legendre神经网络预测方法。该方法运用混沌理论对短期负荷数据进行向空间重构,并以欧式距离选取最佳训练样本,而后采用以Legendre正交多项式为隐含层神经元激励函数的三层神经网络进行训练,并运用训练好的网络进行预测。训练网络时,为了确定网络的最佳拓扑结构,文中引入了衍生算法来确定隐含层神经元的最佳个数。实例分析表明了该方法的可行性,且能得到较高的预测精度和良好的预测效果。
英文摘要:
      Considering the short-term load’s characteristics of chaos and the neural network’s nonlinear mapping ability, this paper puts forward a kind of prediction method which is based on chaos theory and Legendre neural network. The method selects best training samples based on Euclidean distance after using chaos theory to reconstruct space for short-term load data, and then train the network using three layer neural networks whose excitation function of hidden layer is Legendre orthogonal polynomials,at last uses the trained network to forecast. In order to determine the network’s best topological structure when the network is training, this paper introduces derivative algorithm to determine the best number of hidden layer neurons. Example analysis shows that the method is feasible, and can get a high forecasting precision and good prediction effect.
View Full Text   View/Add Comment  Download reader
Close
  • Home
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • 中文页面
Address: No.2000, Chuangxin Road, Songbei District, Harbin, China    Zip code: 150028
E-mail: dcyb@vip.163.com    Telephone: 0451-86611021
© 2012 Electrical Measurement & Instrumentation
黑ICP备11006624号-1
Support:Beijing Qinyun Technology Development Co., Ltd