• 论文 •

### 一种新的快速衰落信道非线性预测算法

1. 西安交通大学 电子与信息学院, 西安 710049
• 收稿日期:2003-11-17 出版日期:2005-05-31 发布日期:2010-11-22
• 作者简介:孙建成(1973-),男,陕西铜川人,博士生, sunjc@mailst.xjtu.edu.cn.
• 基金资助:

国家自然科学基金资助项目(90207012)

### Novel nonlinear prediction algorithm for fast fading channel

Sun Jiancheng, Zhang Taiyi, Liu Feng

1. School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China
• Received:2003-11-17 Online:2005-05-31 Published:2010-11-22

Abstract: Prediction of the rapidly fading mobile radio channel enables a number of capacity improving techniques such as the fast adaptive resource allocation or fast adaptive modulation. To predict the fast fading channel parameters, the embedding phase space was reconstructed by utilizing times delay techniques since the high dimension space possessed more information of system than the scalar time series, and a new nonlinear regression method: recurrent least squares support vector machines (RLS-SVM) was used to resolve the prediction problem in a high space. The fading envelope was well modeled as a Gauss bandlimited process which possessed special predictability properties and the predictability was also analyzed from point of view of nonlinear dynamics. Performance evaluation of the prediction algorithm was carried out with varied signal to noise rate on Rayleigh fading channels. The simulation result shows that the proposed algorithm is a good candidate for long range prediction of fading channel.