Application of independent component analysis in short-term power forecasting of wind farm

Guochu Chen, Peng Wang, Jinshou Yu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

For the difficult problems of measuring and forecasting values interfered by a number of factors, this paper proposed a method of power forecasting based on independent component analysis and least squares support vector machine, and results are modified using the regression. Each independent component from source signals is predicted using least squares support vector machine, the final prediction results obtained by modifying the preliminary predicting power according to the relationship between wind speed and its power. Using the data from a wind farm on the Northeast China wind farm, the simulation results show that this method has higher prediction accuracy, and the mean absolute error from 9.25% down to 5.48%, compared with the simple least squares support vector machine models.

Original languageEnglish
Title of host publicationAdvanced Research on Mechanical Engineering, Industry and Manufacturing Engineering
Pages124-128
Number of pages5
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 International Conference on Mechanical Engineering, Industry and Manufacturing Engineering, MEIME2011 - Beijing, China
Duration: 23 Jul 201124 Jul 2011

Publication series

NameApplied Mechanics and Materials
Volume63-64
ISSN (Print)1660-9336
ISSN (Electronic)1662-7482

Conference

Conference2011 International Conference on Mechanical Engineering, Industry and Manufacturing Engineering, MEIME2011
Country/TerritoryChina
CityBeijing
Period23/07/1124/07/11

Keywords

  • Forecasting
  • Independent component analysis
  • Least squares support vector machine
  • Nonlinear regression
  • Wind power

Fingerprint

Dive into the research topics of 'Application of independent component analysis in short-term power forecasting of wind farm'. Together they form a unique fingerprint.

Cite this