Piecewise Support Vector Machine Model for Short-Term Wind-power Prediction
Authors:
- 7 October 2009
- journal article
- research article
- Published by Taylor & Francis in International Journal of Green Energy
- Vol. 6 (5) , 479-489
Abstract
Based on the characteristics of the power curves of wind turbine generator systems and the principles of the support vector machine (SVM), a piecewise support vector machine (PSVM) model is proposed in this article to improve the precision of short-term wind-power prediction systems. The operation data from a wind farm in north China are used to verify the proposed model, and the average mean error and root mean squared error of the PSVM model are 4.76% and 68.83 kW less than that of an SVM model respectively. Results of parameter optimization confirm the robustness of the PSVM model.Keywords
This publication has 6 references indexed in Scilit:
- Forecast of hourly average wind speed with ARMA models in Navarre (Spain)Solar Energy, 2005
- Novel SrGa[sub 2]O[sub 4] Phosphor for Tunable Blue-White LuminescenceJournal of the Electrochemical Society, 2005
- Support vector machines for wind speed predictionRenewable Energy, 2004
- A comparison of various forecasting techniques applied to mean hourly wind speed time seriesRenewable Energy, 2000
- Short-term prediction of the power production from wind farmsJournal of Wind Engineering and Industrial Aerodynamics, 1999
- Wind power forecasting using advanced neural networks modelsIEEE Transactions on Energy Conversion, 1996