The Comparison of BP Network and RBF Network in Wind Power Prediction Application

Wind power prediction is of great importance for the safety and stabilization of grids. Based on historical data, the application of BP and RBF network in 3 hours wind power prediction are compared. The comparisons are of network structure, network training speed and prediction results. Combined with BP and RBF network, two prediction routes were put forward to predict wind farm power. The results show that, for both BP and RBF network, the relative power prediction error is 11%-14% for each turbine and 8%-10% for the whole wind farm. The training speed and prediction precision of RBF network are superior to those of BP network and the best result is gotten by RBF network. RBF network is suitable for online wind power prediction.

[1]  P. Dokopoulos,et al.  Short-term forecasting of wind speed and related electrical power , 1998 .

[2]  S. Watson,et al.  Short-term prediction of local wind conditions , 1994 .

[3]  Ignacio J. Ramirez-Rosado,et al.  Artificial neural network models for wind power short-term forecasting using weather predictions , 2006 .

[4]  Georges Kariniotakis,et al.  Forecasting of regional wind generation by a dynamic fuzzy-neural networks based upscaling approach , 2003 .

[5]  Pierre Pinson,et al.  Standardizing the Performance Evaluation of Short-Term Wind Power Prediction Models , 2005 .

[6]  M. Milligan,et al.  Statistical Wind Power Forecasting Models: Results for U.S. Wind Farms; Preprint , 2003 .

[7]  Ismael Sánchez,et al.  Short-term prediction of wind energy production , 2006 .

[8]  George Stavrakakis,et al.  Wind power forecasting using advanced neural networks models , 1996 .

[9]  X. Wang,et al.  Wind speed forecasting for power system operational planning , 2005, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[10]  Xiao Yang,et al.  WIND SPEED AND GENERATED POWER FORECASTING IN WIND FARM , 2005 .

[11]  Ioannis B. Theocharis,et al.  Locally recurrent neural networks for long-term wind speed and power prediction , 2006, Neurocomputing.

[12]  Ulrich Focken,et al.  Short-term prediction of the aggregated power output of wind farms—a statistical analysis of the reduction of the prediction error by spatial smoothing effects , 2002 .

[13]  Athanasios Sfetsos,et al.  A novel approach for the forecasting of mean hourly wind speed time series , 2002 .

[14]  N.D. Hatziargyriou,et al.  An Advanced Statistical Method for Wind Power Forecasting , 2007, IEEE Transactions on Power Systems.