A New Pre-distorter Based on Neural Network for the Nonlinear HPA in Satellite Communications

Author

Xu, Yong ; Tong, Xinhai

Author_Institution

Inst. of Commun. & Technol., PLA Univ. of Sci. & Technol., Nanjing, China

fYear

2010

fDate

13-14 Oct. 2010

Firstpage

168

Lastpage

171

Abstract

The Travel-Wave-Tube(TWT) used in the HPA in satellite communications may unexpectedly cause nonlinearity to the signals. A Pre-Distorter(PD) based on a feed-forward neural network will reduce these distortions. To simplify the conventional Levenberg-Marquardt algorithm for neural network, LMS algorithm is employed to reduce the complexity of the learning algorithm and a new scheme is proposed. Simulation results confirm that the proposed pre-distorter based on neural network consisting with one hidden layer and nine neurons gives a good performance improvement.

Keywords

distortion; feedforward neural nets; satellite communication; telecommunication computing; travelling wave amplifiers; travelling wave tubes; LMS algorithm; Levenberg-Marquardt algorithm; TWT; feedforward neural network; high power amplifiers; learning algorithm; nonlinear HPA; predistorter; satellite communications; travel wave tube; Adaptation model; Adaptive systems; Algorithm design and analysis; Artificial neural networks; Least squares approximation; Modulation; Neurons; HPA; LMS; Neural Network; Pre-distortion; TWT;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Intelligence Information Security (ICCIIS), 2010 International Conference on

Conference_Location

Nanning

Print_ISBN

978-1-4244-8649-6

Electronic_ISBN

978-0-7695-4260-7

Type

conf

DOI

10.1109/ICCIIS.2010.53

Filename

5629220