Comparison of BPN and RBF Neural Networks for Prediction of Wind Speed

Abstract -- Prediction of an accurate wind speed of wind farms is necessary because of the intermittent nature of wind. Also, it can relieve or avoid the disadvantageous impact to the electric network. For the purpose, number of methods such as persistence, physical, statistical, spatial correlation, artificial intelligence network and hybrid are generally available for prediction of wind speed.  In the present study, ANN based methods viz., Back Propagation (BPN) and Radial Basis Function (RBF) neural networks are used. The performance of the networks adopted for prediction of wind speed are evaluated by model performance indicators such as Correlation Coefficient (CC), Model Efficiency (MEF) and Mean Absolute Percentage Error (MAPE). Meteorological parameters such as maximum and minimum temperature, air pressure, solar radiation and altitude are considered as input units for BPN and RBF networks to predict the annual extreme wind speed. The optimum network architectures, viz., 5-15-1 of BPN and 5-20-1 of RBF are applied to train the network data. The study shows the values of CC, MEF and MAPE between the observed and predicted wind speed (using BPN network) are computed as 0.995, 96.4% and 2.3% respectively while training the network data. For RBF network, the values of CC, MEF and MAPE are computed as 0.983, 92.3% and 3.1% respectively. The BPN and RBF networks are tested by predicting wind speed for Kanyakumari for which measured data are available; and the results indicate the developed BPN network gives high prediction accuracy. The paper presents the results obtained from BPN network is more accurate than RBF network.

Keywords -- Artificial Neural Network, Back Propagation, Correlation Coefficient, Mean Absolute Percentage Error, Model Efficiency, Radial Basis Function, Wind Speed.


References --

[1]         A.D. Sahin, Progress and recent trends in wind energy, Progress in Energy and Combustion Science 2004, Vol. 30, No. 5, pp. 501-543.

[2]         P. Ramasamy, S.S. Chandel and A.K. Yadav, Wind speed prediction in the mountainous region of India using an artificial neural network model, Renewable Energy, 2015, Vol. 80, pp. 338-347.

[3]         W.Y Chang, A literature review of wind forecasting methods, Journal of Power and Energy Engineering, 2014, Vol. 2, No. 4, pp. 161-168. 

[4]         M. Pallavi, C. Swaptik, R. Sangeeta, B. Nikhil and S. Roshan, Dual artificial neural network for rainfall-runoff forecasting, Journal of Water Resource and Protection, 2012, Vol. 4, No. 12, pp. 1024-1028.

[5]         H.E. Amr, A. El-Shafie, G.E. Hasan, A. Shehata and M.R. Taha, Artificial neural network technique for rainfall forecasting applied to Alexandria, International Journal of the Physical Sciences, 2011, Vol. 6, No. 6, pp. 1306-1316.

[6]         Y.K. Wu, C.Y. Lee, S.H. Tsai and S.N. Yu, Actual experience on the short-term wind power forecasting at Penghu-From an Island perspective. Proceedings of the 2010 International Conference on Power System Technology, Hangzhou, 24-28 October 2010, 1-8 [].

[7]         A. Sfetsos, A novel approach for the forecasting of hourly wind speed time series, Renewable Energy, 2002, Vol. 27, No. 2, pp.163-174.

[8]         W.Y Chang, Wind energy conversion system power forecasting using radial basis function neural network, Applied Mechanics and Materials, 2013, Vol. 284-287, pp. 1067-1071.

[9]         A. More and M.C. Deo, Forecasting wind with neural networks. Marine Structures, 2003, Vol. 16, No. 1, pp. 35-49.

[10]     W.Y Chang, Application of back propagation neural network for wind power generation forecasting. International Journal of Digital Content Technology and its Application, 2013, Vol. 7, No. 4, pp. 502-509.

[11]     G. Li, and J. Shi, On comparing three artificial neural networks for wind speed forecasting, Applied Energy, 2010, Vol. 87, No. 7, pp. 2313-2320.

[12]     J.R. Xia, P. Zhao and Y.P. Dai, Neuro-fuzzy networks for short-term wind power forecasting. Proceedings of the International Conference on Power System Technology, Hangzhou, 24-28 October 2010, pp. 1-5 [].

[13]     Y.M. Wang, S. Traore, T. Kerh, and J.M. Leu, Modelling reference evapotranspiration using feed forward back propagation algorithm in arid regions of Africa,  Irrigation Drainage, 2011, Vol. 60, No. 3, pp. 404–417.

[14]     S. Jalal, K. Özgur, M. Oleg, S.Abbas-Ali  and  N. Bagher, Fore-casting daily stream flows using artificial intelligence approaches, ISH Journal of Hydraulic Engineering, 2012,Vol. 18, No. 3, pp. 204-214.

[15]     L. Ma, S.Y. Luan, C.W. Jiang, H. L. Liu and Y. Zhang, A Review on the forecasting of wind speed and generated power, Renewable and Sustainable Energy Reviews, 2009, Vol. 13, No. 4, pp. 915-920.

[16]     S.K.H. Chow, E.W.M. Lee and D.H.W. Li, Short-term prediction of photovoltaic energy generation by intelligent approach, Energy Build, 2012, Vol. 55, December  issue, pp. 660-667.

[17]     K.P. Sudheer, K. Srinivasan, T.R. Neelakantan and V. Srinivas , A nonlinear data-driven model for synthetic generation of annual streamflows, Hydrological Processes, 2008, Vol. 22, No. 12, pp. 1831-1845.

J. Chen and B.J. Adams, Integration of artificial neural networks with conceptual models in rainfall-runoff modelling, Journal of Hydrology, 2006, Vol. 318, No. 1-4, pp. 232-249.


Click Here To Download Full Article.

About the Author

N. Vivekanandan

N. Vivekanandan

Central Water and Power Research Station, Pune, Maharashtra


Dis Estetigi Liposuction Tstanbul Liposuction istanbul Rhinoplasty Turkey rhinoplasty istanbul cosmetic surgery istanbul Bebek Kiyafetleri sac ekimi Burun Estetigi meme buyutme goz kapagi estetigi goz kapagi estetigi meme kucultme Lazer Lipoliz Karin Germe burun estetigi yuz germe burun estetigi meme estetigi Su Kabagi Gourd Lamps somine burun estetigi

Most Viewed - All Categories