Short-term wind power prediction using least-square support vector machines

Tebello Mathaba; Xiaohua Xia; Jiangfeng Zhang

doi:10.1109/PowerAfrica.2012.6498620

Short-term wind power prediction using least-square support vector machines

Tebello Mathaba
, Xiaohua Xia
, Jiangfeng Zhang

University of Pretoria

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

7 Citations (Scopus)

Abstract

This paper presents a short-term prediction scheme of wind power from wind speed data using Least-Square Support Vector Machines (LS-SVM). The paper develops different LS-SVM models that make use of atmospheric temperature and take advantage of the periodicity of the wind speed data. Results show that atmospheric temperature and using the periodic trend improves the predictions accuracy over the persistence model. The proposed models predict wind power within an error margin of 20% of rated power, 85% of the time.

Original language	English
Title of host publication	IEEE Power and Energy Society Conference and Exposition in Africa
Subtitle of host publication	Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012
DOIs	https://doi.org/10.1109/PowerAfrica.2012.6498620
Publication status	Published - 2012
Externally published	Yes
Event	IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012 - Johannesburg, South Africa Duration: 9 Jul 2012 → 13 Jul 2012

Publication series

Name	IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012

Conference

Conference	IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012
Country/Territory	South Africa
City	Johannesburg
Period	9/07/12 → 13/07/12

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Support Vector Machines
Wind Power Prediction

ASJC Scopus subject areas

Artificial Intelligence
Renewable Energy, Sustainability and the Environment

Access to Document

10.1109/PowerAfrica.2012.6498620

Cite this

Mathaba, T., Xia, X., & Zhang, J. (2012). Short-term wind power prediction using least-square support vector machines. In IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012 Article 6498620 (IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012). https://doi.org/10.1109/PowerAfrica.2012.6498620

Mathaba, Tebello ; Xia, Xiaohua ; Zhang, Jiangfeng. / Short-term wind power prediction using least-square support vector machines. IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012. 2012. (IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012).

@inproceedings{12a546dcb4f54e4db8e1136aaeb8655b,

title = "Short-term wind power prediction using least-square support vector machines",

abstract = "This paper presents a short-term prediction scheme of wind power from wind speed data using Least-Square Support Vector Machines (LS-SVM). The paper develops different LS-SVM models that make use of atmospheric temperature and take advantage of the periodicity of the wind speed data. Results show that atmospheric temperature and using the periodic trend improves the predictions accuracy over the persistence model. The proposed models predict wind power within an error margin of 20\% of rated power, 85\% of the time.",

keywords = "Support Vector Machines, Wind Power Prediction",

author = "Tebello Mathaba and Xiaohua Xia and Jiangfeng Zhang",

year = "2012",

doi = "10.1109/PowerAfrica.2012.6498620",

language = "English",

isbn = "9781467325486",

series = "IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012",

booktitle = "IEEE Power and Energy Society Conference and Exposition in Africa",

note = "IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012 ; Conference date: 09-07-2012 Through 13-07-2012",

}

Mathaba, T, Xia, X & Zhang, J 2012, Short-term wind power prediction using least-square support vector machines. in IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012., 6498620, IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012, IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012, Johannesburg, South Africa, 9/07/12. https://doi.org/10.1109/PowerAfrica.2012.6498620

Short-term wind power prediction using least-square support vector machines. / Mathaba, Tebello; Xia, Xiaohua; Zhang, Jiangfeng.
IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012. 2012. 6498620 (IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012).

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

TY - GEN

T1 - Short-term wind power prediction using least-square support vector machines

AU - Mathaba, Tebello

AU - Xia, Xiaohua

AU - Zhang, Jiangfeng

PY - 2012

Y1 - 2012

N2 - This paper presents a short-term prediction scheme of wind power from wind speed data using Least-Square Support Vector Machines (LS-SVM). The paper develops different LS-SVM models that make use of atmospheric temperature and take advantage of the periodicity of the wind speed data. Results show that atmospheric temperature and using the periodic trend improves the predictions accuracy over the persistence model. The proposed models predict wind power within an error margin of 20% of rated power, 85% of the time.

AB - This paper presents a short-term prediction scheme of wind power from wind speed data using Least-Square Support Vector Machines (LS-SVM). The paper develops different LS-SVM models that make use of atmospheric temperature and take advantage of the periodicity of the wind speed data. Results show that atmospheric temperature and using the periodic trend improves the predictions accuracy over the persistence model. The proposed models predict wind power within an error margin of 20% of rated power, 85% of the time.

KW - Support Vector Machines

KW - Wind Power Prediction

UR - https://www.scopus.com/pages/publications/84877294437

U2 - 10.1109/PowerAfrica.2012.6498620

DO - 10.1109/PowerAfrica.2012.6498620

M3 - Conference contribution

AN - SCOPUS:84877294437

SN - 9781467325486

T3 - IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012

BT - IEEE Power and Energy Society Conference and Exposition in Africa

T2 - IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012

Y2 - 9 July 2012 through 13 July 2012

ER -

Mathaba T, Xia X, Zhang J. Short-term wind power prediction using least-square support vector machines. In IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012. 2012. 6498620. (IEEE Power and Energy Society Conference and Exposition in Africa: Intelligent Grid Integration of Renewable Energy Resources, PowerAfrica 2012). doi: 10.1109/PowerAfrica.2012.6498620

Short-term wind power prediction using least-square support vector machines

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this