A Method for Forecasting Short-Term Wind Speed Based on EMD and SVM

Abstract:

In this paper, a method for wind speed forecasting based on Empirical Mode Decomposition and Support Vector machine is proposed. Compared with the approach based on Support Vector machine only, the method in this paper use EMD to decompose the data of wind power into several independent intrinsic mode functions (IMF),then model each component with the SVM model and get the final value of the overall wind power prediction. Experiments show the efficiency of the approach with a higher forecasting accuracy.

• Periodical: Applied Mechanics and Materials (Volume 392)
• Pages: 622-627
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.392.622
• Online since: September 2013
• Authors: Xiao Jing Dang, Hao Yong Chen, Xiao Ming Jin
• Keywords: Empirical Mode Decomposition (EMD), Support Vector Machine (SVM), Wind Speed Forecasting

References

[1] Pan Difu, Liu Hui, Li Yanfei. A Wind Speed Forecasting Optimization Model for Wind Farms Based on Time Series Analysis and Kalman Filter Algorithm. power system technology. 2008. 32(7): 82-86.

[2] Vapnik V N. Statistical Learning Theory. John Wiley & Sons, Inc. New York, (1998).

[3] Zhang Guoqiang, Zhang Boming. Based on the combination forecasting wind speed and wind turbine power prediction[J]. Automation of Electric Power Systems. 2009. 33 (18): 92-95.

[4] Hippert H S, Pedreira C E, Souza R C. Neural networks for short-term load forecasting: A review and evaluation [J] . IEEE Transon Power System, 2001, 16( 1) : 44 - 55.

DOI: 10.1109/59.910780

[5] Zheng Yanqiu. Short-term load forecasting method based on empirical mode decomposition and neural network [D]. 2009, 5.

[6] Chen Yongyi, Yu Xiaoding, Gao Xuehao, Feng Hanzhong. A new way to deal with nonlinear classification and regression problems _I_ support vector machine Introduction[J]. Journal of Applied Meteorological Science . 2004. 15(3): 345-353.

[7] Bailey B, Brower M C, Zack. Short-term wind forecasting[C]. European Wind Energy Conference, Nice France, 1999.

[8] Qi Shuangbin, Wang Weiqing, Zhang Xinyan. wind speed and wind power prediction method based on support vector machine [J]. East China Electric Power. 2009. 37(9): 1600-1603.

[9] Huang N E, Zheng S, Steven R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear non stationary time Series Analysis [A]. Proceedings: Mathematical, Physical and Engineering Sciences[C]. London, The Royal Society Press, 454(1971).

DOI: 10.1098/rspa.1998.0193