Short-term power prediction of a wind farm based on wavelet analysis

Li Jie Wang; Lei Dong; Xiao Zhong Liao; Yang Gao

Short-term power prediction of a wind farm based on wavelet analysis

Li Jie Wang^*, Lei Dong, Xiao Zhong Liao, Yang Gao

^*Corresponding author for this work

School of Automation

Research output: Contribution to journal › Article › peer-review

72 Citations (Scopus)

Abstract

This paper studied the short-term prediction of wind power generating capacity by means of wavelet analysis and artificial neural network. Signal was decomposed into several sequences in different band by wavelet tranform. By building different neural network, decomposed time series were predicted separately, then the predicted results were added. Some simulations were performed using the real data from Fujin wind farm, China. The results show that the neural network model based on wavelet decomposition improves time lag problem and the mean absolute error drops from 6.99% to 6.01%, compared with the neural network model based on chaotic characteristic.

Original language	English
Pages (from-to)	30-33
Number of pages	4
Journal	Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering
Volume	29
Issue number	28
Publication status	Published - 5 Oct 2009

Keywords

Artificial neural network
Lag characteristic
Power prediction
Wavelet analysis
Wind power generation

Cite this

@article{7ff0a1d3b1f5466083c6b6346f304ebf,

title = "Short-term power prediction of a wind farm based on wavelet analysis",

abstract = "This paper studied the short-term prediction of wind power generating capacity by means of wavelet analysis and artificial neural network. Signal was decomposed into several sequences in different band by wavelet tranform. By building different neural network, decomposed time series were predicted separately, then the predicted results were added. Some simulations were performed using the real data from Fujin wind farm, China. The results show that the neural network model based on wavelet decomposition improves time lag problem and the mean absolute error drops from 6.99\% to 6.01\%, compared with the neural network model based on chaotic characteristic.",

keywords = "Artificial neural network, Lag characteristic, Power prediction, Wavelet analysis, Wind power generation",

author = "Wang, \{Li Jie\} and Lei Dong and Liao, \{Xiao Zhong\} and Yang Gao",

year = "2009",

month = oct,

day = "5",

language = "English",

volume = "29",

pages = "30--33",

journal = "Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering",

issn = "0258-8013",

publisher = "Chinese Society for Electrical Engineering",

number = "28",

}

TY - JOUR

T1 - Short-term power prediction of a wind farm based on wavelet analysis

AU - Wang, Li Jie

AU - Dong, Lei

AU - Liao, Xiao Zhong

AU - Gao, Yang

PY - 2009/10/5

Y1 - 2009/10/5

N2 - This paper studied the short-term prediction of wind power generating capacity by means of wavelet analysis and artificial neural network. Signal was decomposed into several sequences in different band by wavelet tranform. By building different neural network, decomposed time series were predicted separately, then the predicted results were added. Some simulations were performed using the real data from Fujin wind farm, China. The results show that the neural network model based on wavelet decomposition improves time lag problem and the mean absolute error drops from 6.99% to 6.01%, compared with the neural network model based on chaotic characteristic.

AB - This paper studied the short-term prediction of wind power generating capacity by means of wavelet analysis and artificial neural network. Signal was decomposed into several sequences in different band by wavelet tranform. By building different neural network, decomposed time series were predicted separately, then the predicted results were added. Some simulations were performed using the real data from Fujin wind farm, China. The results show that the neural network model based on wavelet decomposition improves time lag problem and the mean absolute error drops from 6.99% to 6.01%, compared with the neural network model based on chaotic characteristic.

KW - Artificial neural network

KW - Lag characteristic

KW - Power prediction

KW - Wavelet analysis

KW - Wind power generation

UR - http://www.scopus.com/inward/record.url?scp=70350584960&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:70350584960

SN - 0258-8013

VL - 29

SP - 30

EP - 33

JO - Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering

JF - Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering

IS - 28

ER -

Short-term power prediction of a wind farm based on wavelet analysis

Abstract

Keywords

Other files and links

Fingerprint

Cite this