Title: One-hour-ahead wind power forecast using hybrid grey models
Authors: Ahmed H. Osman; Mohamed S. Hassan; Fatemeh Marzbani; Taha Landolsi
Addresses: Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE ' Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE ' Department of Electrical Engineering, American University of Sharjah, Sharjah, UAE ' Department of Computer Science and Engineering, American University of Sharjah, Sharjah, UAE
Abstract: This paper proposes two hybrid grey-based short-term wind power prediction techniques: GM(1,1)-ARMA and GM(1,1)-NARnet. These techniques are combined with ARMA models and nonlinear autoregressive neural network (NARnet) models, respectively. The efficiency of these algorithms is examined using a recorded wind power dataset. The performance of these predictors is compared with classical ARMA models as well as the traditional grey model GM(1,1). Unlike the classical predictors, the proposed hybrid algorithms are not affected by the inherent uncertainty in the wind power. Therefore, the results obtained using the proposed hybrid algorithms outperform those obtained using classical predictors. In contrast to the GM(1,1)-ARMA model, the GM(1,1)-NARnet model utilises the nonlinear components of wind power in the forecasting procedure. Consequently, the obtained results from the GM(1,1)-NARnet outperform those obtained by the GM(1,1)-ARMA.
Keywords: wind power forecasting; wind energy prediction; time series analysis; ARMA models; grey theory; GM(1,1); GM(1,1)-ARMA; GM(1,1)-NARnet; neural networks.
International Journal of Operational Research, 2016 Vol.27 No.1/2, pp.212 - 231
Received: 20 Nov 2013
Accepted: 01 May 2014
Published online: 22 Aug 2016 *