Short-term load forecasting using informative vector machine

Eitaro Kurata, Hiroyuki Mori

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this paper, a novel method is proposed for shortterm load forecasting, which is one of the important tasks in power system operation and planning. The load behavior is so complicated that it is hard to predict the load. The deregulated power market is faced with the new problem of an increase in the degree of uncertainty. Thus, power system operators are concerned with the significant level of load forecasting. Namely, probabilistic load forecasting is required to smooth power system operation and planning. In this paper, an IVM (Informative Vector Machine) based method is proposed for short-term load forecasting. IVM is one of the kernel machine techniques that are derived from an SVM (Support Vector Machine). The Gaussian process (GP) satisfies the requirements that the prediction results are expressed as a distribution rather than as points. However, it is inclined to be overtrained for noise due to the basis function with N2 elements for N data. To overcome this problem, this paper makes use of IVM that selects necessary data for the model approximation with a posteriori distribution of entropy. That has a useful function to suppress the excess training. The proposed method is tested using real data for short-term load forecasting.

Original languageEnglish
Pages (from-to)23-31
Number of pages9
JournalElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
Volume166
Issue number2
DOIs
Publication statusPublished - 30 Jan 2009

    Fingerprint

Keywords

  • Gaussian process
  • Informative vector machine
  • Kernel machine
  • Short-term load forecasting

Cite this