A Hybrid Model for Wind Speed Prediction based on Spatial Correlation

DOI

10.2991/msam-15.2015.28How to use a DOI?

Keywords

wind speed forecasting; spatial correlation; coupla functions; state space

Abstract

The accurate prediction of wind speed is greatly significant for evaluating the security and economy of the wind farm which is connected to the grid. This paper proposed a hybrid model for wind speed prediction based on spatial correlation and nonlinear state space model. Firstly, a rank correlation coefficient is calculated according a Coupla function and the coefficient is used to choose the input data of the model. A support vector regression machine is introduced to build a nonlinear state space model, and then a hybrid model is obtained. Finally,experiment results based on some public data are given, the results demonstrate that the proposed hybrid model has higher prediction accuracy and stable performance while comparing with some classical algorithm.

Copyright

© 2015, 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)

TY  - CONF
AU  - Dong Wang
AU  - Jianping Fei
AU  - Haidong Qian
AU  - Yuhong Zhao
PY  - 2015/08
DA  - 2015/08
TI  - A Hybrid Model for Wind Speed Prediction based on Spatial Correlation
BT  - Proceedings of the 2015 International Conference on Modeling, Simulation and Applied Mathematics
PB  - Atlantis Press
SP  - 124
EP  - 127
SN  - 1951-6851
UR  - https://doi.org/10.2991/msam-15.2015.28
DO  - 10.2991/msam-15.2015.28
ID  - Wang2015/08
ER  -