A generalized data preprocessing method for wind power prediction

Jiakun An; Zhaohong Bie; Xiaozhong Chen; Bowen Hua; Shiyu Liu

doi:10.1109/PESMG.2013.6672644

A generalized data preprocessing method for wind power prediction

Jiakun An
, Zhaohong Bie
, Xiaozhong Chen
, Bowen Hua
, Shiyu Liu

School of Electrical Engineering

Xi'an Jiaotong University
Hohai University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

A generalized data preprocessing method is proposed in this paper to reduce the amount of outliers among historical data and further improve the power prediction accuracy. Historical data of wind farms are fit with an S-shape curve via Linear Regression Model. Based on this statistical curve, outliers can be identified considering different fitting error. Furthermore, the expansion of wind farm is identified through the number of outliers. Then a selection method for the allowed maximum fitting errors is recommended. The presented method has been integrated into the prediction system in Inner Mongolia of China with 36 farms. The actual application shows that the wind farm power prediction accuracy has been improved by at least 28% with this model. It is noteworthy that the proposed preprocessing method is just based on statistical analysis of historical data and thus compatible with various wind power prediction methods.

Original language	English
Title of host publication	2013 IEEE Power and Energy Society General Meeting, PES 2013
DOIs	https://doi.org/10.1109/PESMG.2013.6672644
State	Published - 2013
Event	2013 IEEE Power and Energy Society General Meeting, PES 2013 - Vancouver, BC, Canada Duration: 21 Jul 2013 → 25 Jul 2013

Publication series

Name	IEEE Power and Energy Society General Meeting
ISSN (Print)	1944-9925
ISSN (Electronic)	1944-9933

Conference

Conference	2013 IEEE Power and Energy Society General Meeting, PES 2013
Country/Territory	Canada
City	Vancouver, BC
Period	21/07/13 → 25/07/13

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Allowed fitting errors
S-shaped statistical curve
data preprocessing
outliers
samples update
wind farm expansion

Access to Document

10.1109/PESMG.2013.6672644

Cite this

@inproceedings{5bdb99354d274411833fd83eaa3082be,

title = "A generalized data preprocessing method for wind power prediction",

abstract = "A generalized data preprocessing method is proposed in this paper to reduce the amount of outliers among historical data and further improve the power prediction accuracy. Historical data of wind farms are fit with an S-shape curve via Linear Regression Model. Based on this statistical curve, outliers can be identified considering different fitting error. Furthermore, the expansion of wind farm is identified through the number of outliers. Then a selection method for the allowed maximum fitting errors is recommended. The presented method has been integrated into the prediction system in Inner Mongolia of China with 36 farms. The actual application shows that the wind farm power prediction accuracy has been improved by at least 28\% with this model. It is noteworthy that the proposed preprocessing method is just based on statistical analysis of historical data and thus compatible with various wind power prediction methods.",

keywords = "Allowed fitting errors, S-shaped statistical curve, data preprocessing, outliers, samples update, wind farm expansion",

author = "Jiakun An and Zhaohong Bie and Xiaozhong Chen and Bowen Hua and Shiyu Liu",

year = "2013",

doi = "10.1109/PESMG.2013.6672644",

language = "英语",

isbn = "9781479913039",

series = "IEEE Power and Energy Society General Meeting",

booktitle = "2013 IEEE Power and Energy Society General Meeting, PES 2013",

note = "2013 IEEE Power and Energy Society General Meeting, PES 2013 ; Conference date: 21-07-2013 Through 25-07-2013",

}

An, J, Bie, Z, Chen, X, Hua, B & Liu, S 2013, A generalized data preprocessing method for wind power prediction. in 2013 IEEE Power and Energy Society General Meeting, PES 2013., 6672644, IEEE Power and Energy Society General Meeting, 2013 IEEE Power and Energy Society General Meeting, PES 2013, Vancouver, BC, Canada, 21/07/13. https://doi.org/10.1109/PESMG.2013.6672644

TY - GEN

T1 - A generalized data preprocessing method for wind power prediction

AU - An, Jiakun

AU - Bie, Zhaohong

AU - Chen, Xiaozhong

AU - Hua, Bowen

AU - Liu, Shiyu

PY - 2013

Y1 - 2013

N2 - A generalized data preprocessing method is proposed in this paper to reduce the amount of outliers among historical data and further improve the power prediction accuracy. Historical data of wind farms are fit with an S-shape curve via Linear Regression Model. Based on this statistical curve, outliers can be identified considering different fitting error. Furthermore, the expansion of wind farm is identified through the number of outliers. Then a selection method for the allowed maximum fitting errors is recommended. The presented method has been integrated into the prediction system in Inner Mongolia of China with 36 farms. The actual application shows that the wind farm power prediction accuracy has been improved by at least 28% with this model. It is noteworthy that the proposed preprocessing method is just based on statistical analysis of historical data and thus compatible with various wind power prediction methods.

AB - A generalized data preprocessing method is proposed in this paper to reduce the amount of outliers among historical data and further improve the power prediction accuracy. Historical data of wind farms are fit with an S-shape curve via Linear Regression Model. Based on this statistical curve, outliers can be identified considering different fitting error. Furthermore, the expansion of wind farm is identified through the number of outliers. Then a selection method for the allowed maximum fitting errors is recommended. The presented method has been integrated into the prediction system in Inner Mongolia of China with 36 farms. The actual application shows that the wind farm power prediction accuracy has been improved by at least 28% with this model. It is noteworthy that the proposed preprocessing method is just based on statistical analysis of historical data and thus compatible with various wind power prediction methods.

KW - Allowed fitting errors

KW - S-shaped statistical curve

KW - data preprocessing

KW - outliers

KW - samples update

KW - wind farm expansion

UR - https://www.scopus.com/pages/publications/84893199119

U2 - 10.1109/PESMG.2013.6672644

DO - 10.1109/PESMG.2013.6672644

M3 - 会议稿件

AN - SCOPUS:84893199119

SN - 9781479913039

T3 - IEEE Power and Energy Society General Meeting

BT - 2013 IEEE Power and Energy Society General Meeting, PES 2013

T2 - 2013 IEEE Power and Energy Society General Meeting, PES 2013

Y2 - 21 July 2013 through 25 July 2013

ER -

A generalized data preprocessing method for wind power prediction

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this