Wavelet Network with Hybrid Algorithm to Linearize High Power Amplifiers

This paper propose a linearizing scheme based on wavelet networks to reduce nonlinear distortion introduced by a high power amplifier over 256QAM signals. Parameters of the proposed linearizer are estimated by using a hybrid algorithm, namely least square and gradient descent. Computer simulation results confirm that once the 256QAM signals are amplified at an input back off level of 0 dB, there is a reduction of 29 dB spectrum re-growth. In addition proposed linearizing scheme has a low complexity and fast convergence.

[1]  Ying Li,et al.  Data predistortion with adaptive fuzzy systems , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[2]  Jacques Sombrin,et al.  Neural networks for modeling nonlinear memoryless communication channels , 1997, IEEE Trans. Commun..

[3]  D. Serre.  Matrices: Theory and Applications , 2002 .

[4]  Hong‐min Deng,et al.  An adaptive predistorter using modified neural networks combined with a fuzzy controller for nonlinear power amplifiers , 2004 .

[5]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[6]  Qinghua Zhang,et al.  Using wavelet network in nonparametric estimation , 1997, IEEE Trans. Neural Networks.

[7]  Mohamed Ibnkahla,et al.  Neural network predistortion technique for digital satellite communications , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[8]  Peter Gardner,et al.  A novel digital predistorter technique using an adaptive neuro-fuzzy inference system , 2003, IEEE Communications Letters.

[9]  Adel A. M. Saleh,et al.  Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifiers , 1981, IEEE Trans. Commun..

[10]  Peter Gardner,et al.  Adaptive neuro-fuzzy inference system (ANFIS) digital predistorter for RF power amplifier linearization , 2006, IEEE Transactions on Vehicular Technology.

[11]  Daniel Roviras,et al.  Natural gradient algorithm for neural networks applied to non‐linear high power amplifiers , 2002 .

[12]  M. Ibnkahla,et al.  Natural gradient learning neural networks for adaptive inversion of Hammerstein systems , 2002, IEEE Signal Processing Letters.

[13]  R. North,et al.  Predistortion of nonlinear amplifiers using neural networks , 1996, Proceedings of MILCOM '96 IEEE Military Communications Conference.