Author(s)

Zhongxian Men^1,2, Eugene Yee^2,3, Fue-Sang Lien^1,2, Hua Ji¹, Yongqian Liu⁴

¹Waterloo CFD Engineering Consulting Inc., Waterloo, Ontario, Canada.
²Department of Mechanical & Mechatronics Engineering, University of Waterloo, Waterloo, Onatrio, Canada.
³Defence Research and Development Canada, Suffield Research Centre, Medicine Hat, Alberta, Canada.
⁴School of Renewable Energy, North China Electric Power University, Beijing, China.

The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a multi-ANN model super-ensemble for application to multi-step-ahead forecasting of wind speed and of the associated power generated from a wind turbine. A statistical combination of the individual forecasts from the various ANNs of the super-ensemble is used to construct the best deterministic forecast, as well as the prediction uncertainty interval associated with this forecast. The bootstrapped neural-network methodology is validated using measured wind speed and power data acquired from a wind turbine in an operational wind farm located in northern China.

Artificial Neural Network, Bootstrap Resampling, Numerical Weather Prediction, Super-Ensemble, Wind Speed, Power Forecasting

Men, Z. , Yee, E. , Lien, F. , Ji, H. and Liu, Y. (2014) Bootstrapped Multi-Model Neural-Network Super-Ensembles for Wind Speed and Power Forecasting. Energy and Power Engineering, 6, 340-348. doi: 10.4236/epe.2014.611029.