Wind Speed Forecasting Using a Combined Method Based on Auto Regression and Wavelet Transform

Abstract:

This paper presents a new strategy in wind speed prediction based on AR model and wavelet transform.The model uses the adjacent data for short-term wind speed forecasting and the data of the same moment in earlier days for long-term wind speed prediction at that moment,taking the similarity of wind speed at the same moment every day into account.Using the new model to analyze the wind speed of An-xi,China in April,2010,this paper concludes that the model is effective for that the correlation coefficient between the predicted value and the original data is larger than 0.8 when the prediction is less than 48 hours;while the prediction time is long ahead (48-120h),the error is acceptable (within 40%),which demonstrates that the new method is a novel and good idea for prediction on wind speed.

• Periodical: Advanced Materials Research (Volumes 512-515)
• Pages: 803-808
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.512-515.803
• Online since: May 2012
• Authors: Ji Long Tong, Zeng Bao Zhao, Wen Yu Zhang
• Keywords: Auto Regression, Wavelet Transform (WT), Wind Speed Forecasting

References

[1] GWEC,Greenpeace International,et al.The Global Wind Energy Outlook 2010M.Global Wind Energy Council,2010:23-26.

[2] Luo Hai-yang,Liu Tian-qi,Li Xing-yuan.Chaotic Forecasting Method of Short-Term Wind Speed in Wind Farm.Power System Technology,2009,33(9):67-71.

[3] Zhenhai Guo,Jing Zhao,Wenyu Zhang,Jianzhou Wang.A corrected hybrid approach for wind speed prediction in Hexi Corridor of China.Energy 36(2011):1668-1679.

DOI: 10.1016/j.energy.2010.12.063

[4] Michael Milligan,Marc Schwartz,and Yih-huei Wan. Statistical Wind Power Forecasting forU. S.Wind Farms[J]. The 17th Conference on Probability and Statistics in the Atmospheric Sciences/2004 American Meteorological Society Annual MeetingSeattle,Washington January 11-15,2004.

[5] Shuhui Li,Wunsch, D.,O'Hair, E.,Glesselmann M.,Dept. of Electr. Eng.,Texas Tech. Univ,and Lubbock. Using neural networks to estimate wind turbine power generation[J]. IEEE Trans on Energy Conversion,2001,16(3):276-282.

DOI: 10.1109/60.937208

[6] Tai Nengling,Hou Zhijian,Li Tao,Jiang Chuanwen,and Song Jiong.New principle based on wavelet transform for power system short-term load forecasting [J]. Proceedings of the CSEE,2003,23(1):45-50(in Chinese).

[7] CHEN He,ZHOU Shunwu,XIONG Anyuan,LU Yi,LIU Wei.Analysis on Diurnal Variation of Wind Velocity in Hebei.Province Journal of Arid Meteorology.2011,29(3):343-349.

[8] G.H. Riahy,M.Abedi.Short term wind speed forecasting for wind turbine applications using linear prediction method.Renewable Energy 33(2008):35-41.

DOI: 10.1016/j.renene.2007.01.014

[9] Wen-Yu Zhang, Zeng-Bao Zhao, Ting-Ting Han, Ling-Bin Kong.Short Term Wind Speed Forecasting for Wind Farms Using an Improved Autoregression Method. icm, vol. 1 (2011), pp.195-198.

DOI: 10.1109/icm.2011.269

[10] LI Wenliang,WEI Zhinong,SUN Guoqiang,WAN Zheng,MIAO Wei.Multi-interval wind speed forecast model based on improved spatial correlation and RBF neural network.Electric Power Automation Equipment.2009,29(6):89-92.