ガウシアンプロセスによる不確定性を表現した短期電力負荷予測  [in Japanese] A Gaussian Processes Technique for Short-term Load Forecasting with Considerations of Uncertainty  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

In this paper, an efficient method is proposed to deal with short-term load forecasting with the Gaussian Processes. Short-term load forecasting plays a key role to smooth power system operation such as economic load dispatching, unit commitment, <i>etc.</i> Recently, the deregulated and competitive power market increases the degree of uncertainty. As a result, it is more important to obtain better prediction results to save the cost. One of the most important aspects is that power system operator needs the upper and lower bounds of the predicted load to deal with the uncertainty while they require more accurate predicted values. The proposed method is based on the Bayes model in which output is expressed in a distribution rather than a point. To realize the model efficiently, this paper proposes the Gaussian Processes that consists of the Bayes linear model and kernel machine to obtain the distribution of the predicted value. The proposed method is successively applied to real data of daily maximum load forecasting.

Journal

  • IEEJ Transactions on Power and Energy

    IEEJ Transactions on Power and Energy 126(2), 202-208, 2006-02-01

    The Institute of Electrical Engineers of Japan

References:  28

Cited by:  6

Codes

  • NII Article ID (NAID)
    10017153883
  • NII NACSIS-CAT ID (NCID)
    AN10136334
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    03854213
  • NDL Article ID
    7818923
  • NDL Source Classification
    ZN31(科学技術--電気工学・電気機械工業)
  • NDL Call No.
    Z16-794
  • Data Source
    CJP  CJPref  NDL  J-STAGE 
Page Top