Proceedings of the 2017 International Conference on Manufacturing Engineering and Intelligent Materials (ICMEIM 2017)

Power Prediction Research of Wind Farm Based on LS-SVM Multi-model Modeling

Authors
Bei Chen
Corresponding Author
Bei Chen
Available Online February 2017.
DOI
10.2991/icmeim-17.2017.105How to use a DOI?
Keywords
LS-SVM, Multi-model, Affinity Propagation Clustering, Wind Power Prediction
Abstract

Characteristics of multiple working conditions are existed in the medium-term power prediction model of wind farm. To solve this problem, amulti-model modeling method for power prediction based on LS-SVM algorithm is presented. In the method, affinity propagation clustering algorithm is used to cluster the training samples. Then, the sub-models are trained by LS-SVM. The predicted values of the testing samples are forecasted by the sub-models after being classified by the similarity measurement. Finally, experiments of modeling and prediction are arranged by using the wind farm field data. The experiments show that the proposed method has high prediction accuracy and good generalization ability.

Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2017 International Conference on Manufacturing Engineering and Intelligent Materials (ICMEIM 2017)
Series
Advances in Engineering Research
Publication Date
February 2017
ISBN
10.2991/icmeim-17.2017.105
ISSN
2352-5401
DOI
10.2991/icmeim-17.2017.105How to use a DOI?
Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Bei Chen
PY  - 2017/02
DA  - 2017/02
TI  - Power Prediction Research of Wind Farm Based on LS-SVM Multi-model Modeling
BT  - Proceedings of the 2017 International Conference on Manufacturing Engineering and Intelligent Materials (ICMEIM 2017)
PB  - Atlantis Press
SP  - 618
EP  - 623
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmeim-17.2017.105
DO  - 10.2991/icmeim-17.2017.105
ID  - Chen2017/02
ER  -