Neural network based BER prediction for 802.16e channel

Author

Gowrishankar ; Ramesh, B.H.S. ; Satyanarayana, P.S.

Author_Institution

B.M.S. Coll. of Eng., Bangalore

fYear

2007

fDate

27-29 Sept. 2007

Firstpage

1

Lastpage

5

Abstract

The prediction of bit error rate (BER) in IEEE 802.16e mobile wireless MAN network is investigated here. The state of the channel is estimated on symbol by symbol basis on a realistic fading environment. The state of a channel is modeled as nonlinear and temporal system. Neural network method is the best system to predict and analyze the behaviors of such nonlinear and temporal system. In this context, BER prediction by k symbol ahead is investigated by two different recurrent neural network architectures such as recurrent radial basis function (RRBF) network and echo state network (ESN). The predicted BER will match very well with the simulation results.

Keywords

channel estimation; error statistics; fading channels; metropolitan area networks; mobile communication; radial basis function networks; state estimation; BER prediction; IEEE 802.16e mobile wireless MAN network; channel state estimation; echo state network; fading environment; nonlinear system; recurrent neural network; recurrent radial basis function; temporal system; Bit error rate; Fading; Frequency estimation; Frequency synchronization; Neural networks; Nonlinear distortion; OFDM; Predictive models; Quality of service; Wireless networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Software, Telecommunications and Computer Networks, 2007. SoftCOM 2007. 15th International Conference on

Conference_Location

Split-Dubrovnik

Print_ISBN

978-953-6114-93-1

Electronic_ISBN

978-953-6114-95-5

Type

conf

DOI

10.1109/SOFTCOM.2007.4446119

Filename

4446119