FPGA-implementation of an adaptive neural network for RF power amplifier modeling

Author

Bahoura, Mohammed ; Park, Chan-Wang

Author_Institution

Dept. of Eng., Univ. du Quebec a Rimouski, Rimouski, QC, Canada

fYear

2011

fDate

26-29 June 2011

Firstpage

29

Lastpage

32

Abstract

In this paper, we propose an architecture for FPGA-implementation of neural adaptive neural network RF power behavioral modeling. The real-valued time-delay neural network (RVTDNN) and the backpropagation (BP) learning algorithm were implemented on FPGA using Xilinx System Generator for DSP and the Virtex-6 FPGA ML605 Evaluation Kit. Performances obtained with 16-QAM modulated test signal and material resource requirement are presented for a network of six hidden layer neurons.

Keywords

backpropagation; digital signal processing chips; field programmable gate arrays; neural chips; power amplifiers; quadrature amplitude modulation; radiofrequency amplifiers; DSP; QAM modulated test signal; RF power amplifier modeling; Virtex-6 FPGA ML605 evaluation kit; Xilinx system generator; adaptive neural network; backpropagation learning algorithm; neurons; real-valued neural network; time-delay neural network; Adaptation models; Biological neural networks; Field programmable gate arrays; Mathematical model; Microwave communication; Neurons; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

New Circuits and Systems Conference (NEWCAS), 2011 IEEE 9th International

Conference_Location

Bordeaux

Print_ISBN

978-1-61284-135-9

Type

conf

DOI

10.1109/NEWCAS.2011.5981211

Filename

5981211