An Efficient Hybrid Forecasting Approach for Wind Speed Time Series

Bhargavi Munnaluri, K. Ganesh Reddy


Wind forecasting is one of the best efficient ways to deal with the challenges of wind power generation. Due to the depletion of fossil fuels renewable energy sources plays a major role for the generation of power. For future management and for future utilization of power, we need to predict the wind speed.  In this paper, an efficient hybrid forecasting approach with the combination of Support Vector Machine (SVM) and Artificial Neural Networks(ANN) are proposed to improve the quality of prediction of wind speed. Due to the different parameters of wind, it is difficult to find the accurate prediction value of the wind speed. The proposed hybrid model of forecasting is examined by taking the hourly wind speed of past years data by reducing the prediction error with the help of Mean Square Error by 0.019. The result obtained from the Artificial Neural Networks improves the forecasting quality.

Full Text:



A hybrid forecasting approach applied to wind speed time series Jamming Hub*, Jinzhou Wang, Gooey Zeng

T. J. Parr ore and R. G. Miller, “Generalized exponential Markov and model output statistics: a comparative verification,” Monthly Weather Review, vol. 113, pp. 1524–1541, 1985.

M. Bingil, B. Shin, and. Yasser, “Application of artificial neural networks for the wind speed prediction of target station using reference stations data,” Renewable Energy, vol. 32, no. 14, pp. 2350–2360, 2007.

E. Cadenzas and W. Rivera, “Short term wind speed forecasting in La Vento, Oaxaca, Mexico, using artificial neural networks,” Renewable Energy, vol. 34, no. 1, pp. 274–278, 2009.

H. Beyer, T. DeGeneres, J.Hausmann, M.Hoffmann, and P. Roan, “Short term wind speed and power output of a wind turbine with neural networks,” in Proceedings of the 5th European Wind Energy Association Conference and Exhibition, pp. 349–352, 1994

M. A. Mohandas, T. O. Malawian, S. Redman, and A. A. Husain, “Support vector machines for wind speed prediction,” Renewable Energy, vol. 29, no. 6, pp. 939–947, 2004.

Canvasser RG, Seetharaman K. Day-ahead wind speed forecasting using f-ARIMA models. Renew Energy 2009; 34:1388e93.

Mohandas M, Malawian T, Redman S, Husain AA. Support vector machines for wind speed prediction. Renew Energy 2004; 29:939e47

C. Cortes and V. N. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.



  • There are currently no refbacks.

© International Journals of Advanced Research in Computer Science and Software Engineering (IJARCSSE)| All Rights Reserved | Powered by Advance Academic Publisher.