Short-term load forecasting based on input dimension reduction

Tao Xu, Renmu He, Peng Wang, Dongjie Xu

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


The traditional methods for load forecasting can not achieve the required accuracy for some engineering application due to the limited history data sets and the complex factors that affect the load forecasting. This paper presents a framework for the power system short-term load forecasting. It establishes the feature selection model and uses floating search method to find the feature subset. It makes use of the support vector machines (SVM) to forecast the load and takes full advantage of the SVM to solve the problem with small sample and of nonlinear. The accuracy of the estimation result is improved and a better generalization ability is achieved. The EUNITE network is employed to demonstrate the validity of the proposed approach.

Original languageEnglish
Pages (from-to)51-54+81
JournalDianli Xitong Zidonghua/Automation of Electric Power Systems
Issue number6
StatePublished - 25 Mar 2004
Externally publishedYes


  • Feature selection
  • Floating search
  • Load forecasting
  • Support vector machine


Dive into the research topics of 'Short-term load forecasting based on input dimension reduction'. Together they form a unique fingerprint.

Cite this