A Data Mining-Based Wind Power Forecasting Method: Results for Wind Power Plants in Turkey

With the huge technological and industrial developments in recent years, the electricity demand of all countries has been increasing day by day. In order to supply the electricity needs, countries have been looking for ways of benefitting from their renewable energy sources efficiently and wind energy is an important and ubiquitous renewable energy source. However, due to wind's discontinuity and unstable characteristics, a reliable wind forecasting system is crucial not only for transmission system operators but also wind power plant WPP owners. This paper presents a reliable forecasting method based on data mining approaches. The method uses numerical weather predictions and past power measurements of the WPPs as input and it produces hourly short-term wind power forecasts for the WPPs for a time period of 48 hours. The method has been tested in the Wind Power Monitoring and Forecast Center Răi¾?TM project of Turkey for a duration of six months for 14 WPPs. The proposed model achieves better accuracy performance rates than those of the other well-known forecasting models for seven of WPPs selected for the testing procedure by the General Directorate of Renewable Energy in Turkey.

[1]  Kenny C. S Kwok,et al.  MC4 Wind Energy And Topography 2 , 2006 .

[2]  Alan Russell,et al.  Computational Fluid Dynamics Modeling of Atmospheric Flow Applied to Wind Energy Research , 2009 .

[3]  Siddheswar Ray,et al.  Determination of Number of Clusters in K-Means Clustering and Application in Colour Image Segmentation , 2000 .

[4]  Vladimiro Miranda,et al.  Wind power forecasting in U.S. Electricity markets , 2010 .

[5]  F. Oyague,et al.  Wind Energy's New Role in Supplying the World's Energy: What Role will Structural Health Monitoring Play? , 2009 .

[6]  Stanley G. Benjamin,et al.  Global Ensemble Predictions of 2009’s Tropical Cyclones Initialized with an Ensemble Kalman Filter , 2011 .

[7]  Andrew Kusiak,et al.  Wind farm power prediction: a data‐mining approach , 2009 .

[8]  Matthias Lange,et al.  Analysis of the uncertainty of wind power predictions , 2003 .

[9]  Rui Castro,et al.  Wind Speed and Wind Power Forecasting using Statistical Models: AutoRegressive Moving Average (ARMA) and Artificial Neural Networks (ANN) , 2012 .

[10]  Vladimiro Miranda,et al.  Wind power forecasting : state-of-the-art 2009. , 2009 .

[11]  Turan Demirci,et al.  The architecture of a large-scale wind power monitoring and forecast system , 2013, 4th International Conference on Power Engineering, Energy and Electrical Drives.

[12]  Lucie Pokorná,et al.  On the Integrability of Limited-Area Numerical Weather Prediction Model ALADIN over Extended Time Periods , 2003 .

[13]  Atsushi Yamaguchi,et al.  A Physical Approach to Wind Speed Prediction for Wind Energy Forecasting , 2006 .