|
|||||
|
|
| 基于相空间重构的神经网络短期风速预测 | |
| 引用本文： | 廖志强,李太福,余德均,程杨,姚立忠.基于相空间重构的神经网络短期风速预测[J].江南大学学报(自然科学版),2012,11(1):14-18. |
| 作者姓名： | 廖志强 李太福 余德均 程杨 姚立忠 |
| 作者单位： | 1. 西安石油大学电子工程学院,陕西西安,710065 2. 重庆科技学院电气与信息学院,重庆,401331 3. 重庆电力高等专科学校实践教学部,重庆,400053 4. 重庆市农业科学院,重庆,401329 |
| 基金项目： | 国家自然科学基金，重庆市自然科学基金 |
| 摘 要： | 针对风速具有较强的混沌特性,预测难度较大,提出了一种基于相空间重构的神经网络短期风速预测方法:对数据进行小波降噪,运用互信息法和虚假最近邻点法确定最佳的延迟时间和嵌入维数,对样本空间进行重构,使新的样本能够表征原始时间序列动态特性,更能反映风速变化特性。在此基础上运用BP神经网络进行短期风速预测。实验结果表明短期风速预测精度得到提高。 |
| 关 键 词： | 相空间重构 互信息法 虚假最近邻点法 BP神经网络 风速预测 |
Short-Term Wind Speed Forecasting of Neural Network Based on Phase Space Reconstruction |
|
| LIAO Zhi-qiang , LI Tai-fu , YU De-jun , CHENG Yang , YAO Li-zhong.Short-Term Wind Speed Forecasting of Neural Network Based on Phase Space Reconstruction[J].Journal of Southern Yangtze University:Natural Science Edition,2012,11(1):14-18. | |
| Authors: | LIAO Zhi-qiang LI Tai-fu YU De-jun CHENG Yang YAO Li-zhong |
| Institution: | 1(1.College of Electronic Engineering,Xi’an Shiyou University,Xi’an 710065,China;2.Department of Electrical and Information Engineering,Chongqing University of Science and Technology,Chongqing 401331,China;3.Department of Teaching Practice,Chongqing Electric Power College,Chongqing 400053,China;4.Chongqing Academy of Agricultural Sciences,Chongqing 401329,China) |
| Abstract: | Considering the wind speed built-in a strong chaos characteristic and difficult to forecast,a short-term wind speed prediction method based on phase space reconstruction and neural network is proposed to predict wind speed data of time series.The data noises are reduced by wavelet de-noising.Optimal delay time is obtained by mutual information method and embedding dimension is also calculated by false nearest neighbor(FNN) method which reconstructed the sample space.The new space can not only be characterized by the dynamic characteristics of the original time series but also reflect the characteristics of wind.Finally,BP network can be used to forecast short-term wind speed.The experimental results show that the accuracy of short-term wind speed prediction is improved. |
| Keywords: | phase space reconstruction mutual information method false nearest neighbor BP-NN wind speed forecast |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |