Adaptive Predistortions Based on Neural Networks Associated with Levenberg-Marquardt Algorithm for Satellite Down Links - Archive ouverte HAL Access content directly
Journal Articles EURASIP Journal on Wireless Communications and Networking Year : 2008

Adaptive Predistortions Based on Neural Networks Associated with Levenberg-Marquardt Algorithm for Satellite Down Links

Abstract

This paper presents adaptive predistortion techniques based on a feed-forward neural network (NN) to linearize power amplifiers such as those used in satellite communications. Indeed, it presents the suitable NN structures which give the best performances for three satellite down links. The first link is a stationary memoryless travelling wave tube amplifier (TWTA), the second one is a nonstationary memoryless TWT amplifier while the third is an amplifier with memory modeled by a memoryless amplifier followed by a linear filter. Equally important, it puts forward the studies concerning the application of different NN training algorithms in order to determine the most prefermant for adaptive predistortions. This comparison examined through computer simulation for 64 carriers and 16-QAM OFDM system, with a Saleh's TWT amplifier, is based on some quality measure (mean square error), the required training time to reach a particular quality level, and computation complexity. The chosen adaptive predistortions (NN structures associated with an adaptive algorithm) have a low complexity, fast convergence, and best performance.
Fichier principal
Vignette du fichier
132729.pdf (7.54 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-01126471 , version 1 (01-02-2022)

Licence

Attribution

Identifiers

Cite

Rafik Zayani, Ridha Bouallegue, Daniel Roviras. Adaptive Predistortions Based on Neural Networks Associated with Levenberg-Marquardt Algorithm for Satellite Down Links. EURASIP Journal on Wireless Communications and Networking, 2008, 2008 (1), pp.00. ⟨10.1155/2008/132729⟩. ⟨hal-01126471⟩

Collections

CNAM CEDRIC-CNAM
41 View
6 Download

Altmetric

Share

Gmail Facebook X LinkedIn More