Short Term Wind Speed Forecast Revision Method Based on Volatility Characteristics and Confidence Level

Abstract:

Accurately forecasting short-term wind speed can effectively reduce the adverse effects of wind power in power systems and improve the competition of wind power in power markets. Because of the wind randomness, there are huge forecasting errors existing in those commonly used forecasting methods at wind mutation points, and through improving the forecasting method itself can merely provide positive effect. From the angle of revision, a new method is going to be proposed and applied to revise the forecasted wind speed in this paper, which is based on the historical data fluctuation characteristics and confidence level. Under this method, we can turn the original forecasted wind speed into the optimized wind speed. The revision method can be applied on all short-term wind forecast methods. The validity and feasibility of this method are going to be verified through a wind speed forecasting method based on the Grey model GM(1,1).

• Periodical: Advanced Materials Research (Volumes 816-817)
• Pages: 1260-1264
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.816-817.1260
• Online since: September 2013
• Authors: Shi Qian Wang, Li Di, Jing Hui Huang, Chun Zheng Tian
• Keywords: Confidence Level, Data Revision, Volatility Characteristics, Wind Power, Wind Speed Forecast

References

[1] M. Yang, H. Xiong and G. K. Yan. Real-time prediction of wind power based on data mining and fuzzy clustering , Power System Protection and Control, vol. 41, pp.1-6, Jab. (2013).

[2] G. l. Gu, Wang W. Q, X. Y. Zhang. Study of wind speed forecasting method in wind farm, Agricultural Engineering Technology (New Energy Industry), vol. 41, pp.22-24, Jab. (2009).

[3] X. Y. Qing, F. W. Yang. Short-Term Wind Speed Forecasting For Multiple Wind Farms Using Bayesian-Kriged-kalman Mode, Proceedings of CSEE, vol. 35, pp.107-114, Apr. (2012).

[4] J.L. Torres, Garcia A, Blas M D, et a1. Forecast of Hourly Average Wind Speed with ARMA Models in Navarre(Spain) ,. Solar Energy, vol. 79, pp.65-77, Mar. (2005).

DOI: 10.1016/j.solener.2004.09.013

[5] H. Y. Zhang, Y. H. Yin. A Wind Speed Time Series Modelling Method Based on Probability Measure Transformation, Automation of Electric Power Systems, vol. 37, pp.7-10, Jab. (2013).

[6] Barbounis T G, Theocharis J B, Alexiadis M C. Long-term Wind Speed and Power Forecasting Using Local Recurrent Neural Network Models,. Transactions on Energy Conversion, vol. 21, pp.273-284, Mar. (2006).

DOI: 10.1109/tec.2005.847954

[7] Alexiadis M, Dokopoulos P, Sahsamanoglou H. Short term forecasting of wind speed and related electrical power,. Solar Energy, vol. 63, pp.61-68, Jab. (1998).

DOI: 10.1016/s0038-092x(98)00032-2