A Robust Algorithm for Wind Power Forecasting Based on Projection Pursuit and Back Propagation Neural Network

Wen Xia Liu; Ying Zhi Li

doi:10.4028/www.scientific.net/AMM.291-294.429

Paper Titles

Research on Wind Power Fluctuation and its Impacts on Power System Frequency
p.407

The Research of Finite Element Modeling and Contacts for Connecting Bolts of Wind Turbine
p.415

A Discussion of the Impact of Building Wind Deflector on Changes in Wind Field by Using the Numerical Simulation
p.419

A New Method for Horizontal Axis Wind Turbine Angle of Attack Determination
p.425

A Robust Algorithm for Wind Power Forecasting Based on Projection Pursuit and Back Propagation Neural Network
p.429

A Study of Electricity Generating from Small Multi-Blade Wind Turbine for a Household
p.435

Comparison of Archimedean Screw and Normal Pump in Pumped Storage Generation Combined with Wind Power Generation
p.439

Field Experiment of Blade Surface Pressure of a HAWT
p.445

Large-Eddy Simulation of Flow around a Horizontal-Axis Wind Turbine
p.450

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 291-294A Robust Algorithm for Wind Power Forecasting...

A Robust Algorithm for Wind Power Forecasting Based on Projection Pursuit and Back Propagation Neural Network

Abstract:

This paper has proposed a wind farm generation output forecasting model based on projection pursuit (PP) and back propagation neural network (BPNN), in order to eliminate the influence of the bad points and mutations on and enhance robustness of the forecasting model. A median absolute deviation is used as projection index function, effectively avoiding the influence of the outlier. Firstly, Extract the principal components of each factor by PP. Then, input the principal components to the BPNN for training the network. Finally, forecast the wind farm generation output via the trained network. The simulation shows that the proposed approach is of higher accuracy.

You might also be interested in these eBooks

Advances in Energy Science and Technology

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 291-294)

Pages:

429-434

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.291-294.429

Citation:

Cite this paper

Online since:

February 2013

Authors:

Wen Xia Liu, Ying Zhi Li

Keywords:

BP Neural Network (BPNN), Forecasting, Projection Pursuit, Wind Farm Generation Output

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] El-Fouly T.H.M., El-Saadany E.F., Salama, M.M. A: Generation, Transmission & Distribution. Vol. 1 (2007), p.928.

Google Scholar

[2] Liying Zhang, Tinglu Ye, Yaozhong Xin, et al: Proceedings of the CSEE, Vol. 30 (2010), p.1. In Chinese.

Google Scholar

[3] Lijie Wang, Xiaozhong Liao, Yang Gao, et al: Power System Protection and Control, Vol. 37(2009), p.118. In Chinese.

Google Scholar

[4] Junfang Li, Buhan Zhang, Guanglong Xie, et al: Power System Protection and Control, Vol. 38 (2010), p.151. In Chinese.

Google Scholar

[5] I.G. Damousis, M.C. Alexiadis, J.B. Theocharis, P.S. Dokopoulos: Energy Conversion, Vol. 2 (2004), p.352.

Google Scholar

[6] Gaofeng Fan, Weisheng Wang, Chun Liu, et al.: Proceedings of the CSEE, Vol. 28 (2008), p.118. In Chinese.

Google Scholar

[7] Xiaomei Wu, Yin-ming Bai, Fushuan Wen: Power System Protection and Control, Vol. 9 (2011), p.80. In Chinese.

Google Scholar

[8] Wen Luo, Lina Wang: Transactions of China Electro technical Society, Vol. 26(2011), p.68. In Chinese.

Google Scholar

[9] A. Sfetsos: Renew able Energy, Vol. 21 (2000), p.23.

Google Scholar

[10] Mingli Zhang, Xiaoliang Yang, Yun Teng, et al: Power System Technology, Vol. 35 (2011), p.183. In Chinese.

Google Scholar

[11] Ying Song, Xin Tian: Acta Biophysica Sinica, Vol. 17(2001), p.661. In Chinese.

Google Scholar

[12] C. Croux, P. Filzmoser, M.R. Oliveira: Chemometrics and Intelligent Laboratory Systems, Vol. 2(2007), p.218.

Google Scholar