• DocumentCode
    460893
  • Title

    Applying Support Vector Machine Method to Forecast Electricity Consumption

  • Author

    Yang, Shu-Xia ; Wang, Yi

  • Author_Institution
    Sch. of Bus. Adm., North China Electr. Power Univ., Beijing
  • Volume
    1
  • fYear
    2006
  • fDate
    Nov. 2006
  • Firstpage
    929
  • Lastpage
    932
  • Abstract
    Electricity consumption reflects the electricity usage of the whole society, so the prediction study and analysis to electricity consumption have important realistic and theoretical significance. The influence that different factors affect the electricity consumption is in different degrees. And the influence works in complicated ways, which makes the characteristics of the electricity consumption forecast take on complexity, linearity and so on. To enhance the precision of the electricity consumption forecast, this paper adopts the support vector machine method to analyze the statistical data which influences electricity consumption with the aid of the computer and discover the intrinsic rule. This paper puts forward the corresponding electricity consumption forecasting model, and carries on the forecast to the electricity consumption with the actual data from 1980 to 2004, the result indicates that it´s an accurate method to predict the electricity consumption
  • Keywords
    load forecasting; power consumption; power engineering computing; statistical analysis; support vector machines; electricity consumption; electricity usage; forecasting model; prediction analysis; statistical data; support vector machine; Artificial neural networks; Data analysis; Economic forecasting; Energy consumption; Learning systems; Machine learning algorithms; Predictive models; Support vector machine classification; Support vector machines; Time series analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence and Security, 2006 International Conference on
  • Conference_Location
    Guangzhou
  • Print_ISBN
    1-4244-0605-6
  • Electronic_ISBN
    1-4244-0605-6
  • Type

    conf

  • DOI
    10.1109/ICCIAS.2006.294275
  • Filename
    4072228