Implementation of a NARX neural network in a FPGA for modeling the inverse characteristics of power amplifiers

In this paper the hardware implementation of a NARX neural network algorithm using a Field Programmable Gate Array (FPGA) is presented. A NARX network is a Recurrent Neural Network (RNN) suitable for modeling nonlinear systems with promising results for the modeling of the inverse characteristics (AM/AM and AM/PM) of Power Amplifiers (PAs). The implementation is realized in the Xilinx ISE tool with the Virtex-6 FPGA ML 605 Evaluation Kit using Verilog language. Experimental results have shown a high correlation with the inverse model computed with SystemVue in co-simulation with MATLAB for a GaN class F PA working with a LTE signal center at 2 GHz.

[1]  R. D. Lorenz,et al.  A structure by which a recurrent neural network can approximate a nonlinear dynamic system , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[2]  Francisco Sandoval Hernández,et al.  FPGA implementation of a systems identification module based upon Hopfield networks , 2007, Neurocomputing.

[3]  Chan-Wang Park,et al.  FPGA-implementation of an adaptive neural network for RF power amplifier modeling , 2011, 2011 IEEE 9th International New Circuits and systems conference.

[4]  W. F. H. Abdullah,et al.  Design of single neuron on FPGA , 2012, 2012 IEEE Symposium on Humanities, Science and Engineering Research.

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[6]  F.M. Ghannouchi,et al.  Adaptive Digital Predistortion of Wireless Power Amplifiers/Transmitters Using Dynamic Real-Valued Focused Time-Delay Line Neural Networks , 2010, IEEE Transactions on Microwave Theory and Techniques.

[7]  Hava T. Siegelmann,et al.  Computational capabilities of recurrent NARX neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[8]  Zoran Salcic,et al.  Digital Systems Design and Prototyping Using Field Programmable Logic , 1997 .

[9]  Hans-Georg Zimmermann,et al.  Recurrent Neural Networks Are Universal Approximators , 2006, ICANN.

[10]  C. L. Giles,et al.  Learning long { term dependencies is not asdi cult with NARX recurrent neural , 1996 .

[11]  Jürgen Becker,et al.  Performance, accuracy, power consumption and resource utilization analysis for hardware / software realized Artificial Neural Networks , 2010, 2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA).