Support Vector Machine-Based Short-Term Wind Power Forecasting

Authors

Jianwu Zeng, University of Nebraska-LincolnFollow
Wei Qiao, University of Nebraska–LincolnFollow

Document Type

Article

Date of this Version

3-2011

Comments

Published in the Proceedings of the 2011 IEEE PES Power System Conference and Exposition, held in Phoenix, Arizona, U.S.A., March 20-23, 2011.
ISBN: 978-1-61284-788-7. Copyright 2011, IEEE. Used by permission.

Abstract

This paper proposes a support vector machine (SVM)-based statistical model for wind power forecasting (WPF). Instead of predicting wind power directly, the proposed model first predicts the wind speed, which is then used to predict the wind power by using the power-wind speed characteristics of the wind turbine generators. Simulation studies are carried out to validate the proposed model for very short-term and short-term WPF by using the data obtained from the National Renewable Energy Laboratory (NREL). Results show that the proposed model is accurate for very short-term and short-term WPF and outperforms the persistence model as well as the radial basis function neural network-based model.