|
|
Prediction Algorithm for Fast Fading Channels Based on
Recurrent Least Squares Support Vector Machines |
Xiang Zheng①②; Zhang Tai-yi①; Sun Jian-cheng① |
①Dept. of Electronics and Information Eng., Xi’an Jiaotong Univ., Xi’an 710049, China;②School of Telecommunication Engineering, Xidian Univ., Xi’an 710071, China |
|
|
Abstract An new method for fast fading channel prediction using Recurrent Least Squares Support Vector Machines (RLS-SVM) combined with reconstructed embedding phase space is investigated. This algorithm is based on the chaotic behavior of the mobile multipath fading channel.The phase space of these mobile multipath fading channel coefficients are reconstructed by the theory of time delays. Based on the stability and the fractal of the chaotic attractor, the fast fading channel coefficients are predicted in their phase space based on the RLS-SVM.The proposed algorithm is a better candidate for long range prediction of the fading channel in the noise context . The experiment is carried out by utilizing fading channel data which spanes 63.829 ms. The simulation results show that the better prediction performance is acquired than the AR method when the signal to noise ratio is 15dB.
|
Received: 24 June 2005
|
|
|
|
|
|
|
|