Nonlinear prediction of mobile-radio fading channel using recurrent least squares support vector machines and embedding phase space

Prediction of the rapidly fading mobile-radio channel enables a number of capacity improving techniques, such as fast resource allocation or fast adaptive modulation. We construct an embedding phase space which includes more system information than the scalar time series; then we use a new nonlinear regression method, recurrent least squares support vector machines (RLS-SVM), to resolve the prediction problem. A performance evaluation of the prediction algorithm is carried out with various SNR values on Rayleigh fading channels. The simulation results show that the proposed algorithm is a good method for long range prediction of the fading channel.