Wind speed forecasting using wavelet network based on a structure optimization method
- DOI
- 10.2991/icitmi-15.2015.122How to use a DOI?
- Keywords
- grey correlation-contribution pruning method; structure optimization; wind speed forecasting; wavelet network
- Abstract
Accurate forecasting of wind speed is significant to the safe and stable operation of wind power system. In this paper, a structure optimization method is proposed and used to improve the accuracy of wavelet network wind speed forecasting model. In the training process of wavelet network, grey correlation pruning method is applied to optimize the hidden layer nodes firstly, until the grey correlation pruning coefficients of the remaining hidden nodes are greater than grey correlation pruning threshold. Secondly, contribution pruning method is applied to optimize the hidden layer nodes, until the contribution pruning coefficients of the remaining hidden nodes are greater than contribution pruning threshold. Finally wind speed forecasting model is built with optimized wavelet network. Experiment results show that using the grey correlation-contribution pruning method to optimize wavelet network can simplify the network structure, and the performances of the optimized wind speed model have been improved obviously compared with the wavelet network without structure optimization.
- 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/).
Cite this article
TY - CONF AU - Xiao-Yang Liu AU - Fang Wang AU - Jian-Yan Tian AU - Shu-Jie Gao PY - 2015/10 DA - 2015/10 TI - Wind speed forecasting using wavelet network based on a structure optimization method BT - Proceedings of the 4th International Conference on Information Technology and Management Innovation PB - Atlantis Press SP - 733 EP - 738 SN - 2352-538X UR - https://doi.org/10.2991/icitmi-15.2015.122 DO - 10.2991/icitmi-15.2015.122 ID - Liu2015/10 ER -