The Forecasting of Short-Term Wind Speed on Wind Farm Based on Phase Space Reconstruction and Neural Network

Abstract:

The forecasting precision of short-term wind speed is not high for its chaos and time-varying. Aimed at the problem, the novel data space is reconstructed with the best embedding dimension and time delay according to the phase space reconstruction. On the basis, neural network (NN) is used as the modeling tool with the novel sample data. Meanwhile, the structure of NN is confirmed compared with the others on the precision. In the end, the model of short-term wind speed is able to be obtained. The results show that the method is available and the Mean absolute error (MAE) is decreased to 16.2% for 2 hours.

• Periodical: Applied Mechanics and Materials (Volumes 246-247)
• Pages: 496-500
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.246-247.496
• Online since: December 2012
• Authors: Ying Ying Su, Fei Ma, Hai Yan Zhang, Zhi Qiang Liao, Peng Jun
• Keywords: Embedding Dimension, Neural Network (NN), Phase Space Reconstruction, Short-Term Wind Speed, Time Delay

References

[1] Xiuyuan Yang, Yang Xiao, Shuyong Chen, Wind speed and generated power forecasting in wind farm, Proceedings of the CSEE, vol. 25, no. 11 (2005), pp.1-5.

[2] A. P. Schmidt, The persistence, forecasting, and valuation implications of the tax change component of earnings, Accounting Review, (2006), pp.589-616.

DOI: 10.2308/accr.2006.81.3.589

[3] P. Louka, G. Galanis, N. Siebert, G. Kariniotakis, P. Katsafados, I. Pytharoulis and G. Kallos, Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering, Journal of Wind Engineering and Industrial Aerodynamics, vol. 96, (2008).

DOI: 10.1016/j.jweia.2008.03.013

[4] Ming Ding etc., Wind speed forecast model for wind farms based on time series analysis, Electric Power Automation Equipment, vol. 25, no. 8 (2005), pp.32-34.

[5] E. Erdem and J. Shi, ARMA based approaches for forecasting the tuple of wind speed and direction, Applied Energy, vol. 88 (2011), pp.1405-1414.

DOI: 10.1016/j.apenergy.2010.10.031

[6] T.G. Barbounis, J.B. Theocharis, Locally recurrent neural networks for wind speed prediction using spatial correlation, Information Science, no. 177, (2007), pp.5775-5797.

DOI: 10.1016/j.ins.2007.05.024

[7] S. Salcedo-Sanz, Á. M. Pérez-Bellido, E. G. Ortiz-García, A. Portilla-Figueras, L. Prieto and F. Correoso, Accurate short-term wind speed prediction by exploiting diversity in input data using banks of artificial neural networks, Neuro Computing, vol. 72, (2009).

DOI: 10.1016/j.neucom.2008.09.010

[8] H. Luo, T. Liu and X. Li, Chaotic forecasting method of short-term wind speed in wind farm, Power System Technology, vol. 33, no. 9, (2009), pp.67-71.