Predistortion System Implementation Based On Analog Neural Networks For Linearizing High Power Amplifiers Transfer Characteristics

Mulliez, B.; Moutaye, E.; Tap, H.; Gatet, L.; Gizard, F.

doi:10.21307/ijssis-2017-662

Abstract

In order to correct non-linearities due to High Power Amplifiers (HPA) operating near saturation in telecommunication transceivers, a new adaptive predistortion system based on analog Neural Networks (NNs) was developed. Based on size, consumption and bandwidth considerations, Multi-Layer Perceptron (MLP) type NNs were implemented in a 0.6 μm CMOS ASIC. The NNs parameters are digitally updated with a computer, depending on simulation conditions (temperature drifts, ageing variations). The interface between the analog part and the software updating system is integrated in an analog-digital PCB including a FPGA, 6 analog-to-digital converters and 62 digital-to-analog converters. This paper describes the realization of each part of the breadboard system and presents experimental validation results of the whole predistortion module.

References

J. B. Sombrin, “Optimisation criteria for power amplifiers”, in International Journal of Microwave and Wireless Technologies, 2011.10.1017/S1759078710000863
Search in Google Scholar Back to article
S. Bouchired et al., “Equalization of satellite mobile channels with neural network techniques”, in Space Communications 15, IOS Press, pp. 209-220, 1998-99.
Search in Google Scholar Back to article
S. Bouchired et al., “Neural Networks: A Tool for Satellite UMTS Channel Equalization”, in Proceedings of DSP 98, Nordwick, The Netherlands, Sept. 1998.
Search in Google Scholar Back to article
F. Langlet et al., “Adaptive predistortion for Solid State Power Amplifier using Multi-Layer Perceptron”, in Proceedings of Globcom 2001, pp. 325-329, San Antonio, Texas, Nov. 2001.
Search in Google Scholar Back to article
F. Langlet et al., “Comparison of Neural Network Adaptative predistortion Techniques for Satellite Down Links”, in Proceedings of IJCNN 2001, pp. 709-714, Washington DC, July 2001.
Search in Google Scholar Back to article
G. Lazzarin et al., “Nonlinearity Compensation in Digital Radio Systems”, in IEEE Transactions on Communications, Vol. 42, No. 2/3/4, pp. 989-999, Feb./March/April 1994.10.1109/TCOMM.1994.580207
Search in Google Scholar Back to article
A. Saleh, “Frequency-independent and frequency-dependant non linear models of TWT amplifiers”, in IEEE Transactions on Communications, Vol. COMM 29, No. 11, pp. 1715-1720, Nov. 1981.
Search in Google Scholar Back to article
S. Yi, et al., “Prediction of a CDMA output spectrum based on intermodulation products of two-tone test”, in IEEE Transactions on Microwave Theory and Techniques, Vol. 49, No. 5, pp. 938–946, May 2001.10.1109/22.920152
Search in Google Scholar Back to article
V. Volterra, “Theory of Functionals and of Integral of Integro-Differential Equations”, in Dover Publications, Inc, N.Y., 1958.
Search in Google Scholar Back to article
Y.Yang et al., “New Linearization Method for the Modulated Signals with High Peak-to-Average Ratio : Peak-to-Average Ratio Reduction and Expension”, in IEEE MTT-S Digest, pp. 777-780, 2002.
Search in Google Scholar Back to article
H. M. Park et al., “A New predistortion Linearizer Using Envelope-Feedback Technique for PCS High Power Amplifier Application”, in IEEE Radio and Wireless Conference, pp. 223-226, Aug. 1999.
Search in Google Scholar Back to article
B. Beliczynski, “Incremental approximation by one-hidden-layer neural networks: discrete functions rapprochement”, in Proceedings of the IEEE International Symposium on Industrial Electronics (ISIE ‘96), Vol. 1, pp. 392-397, 17-20 June 1996.
Search in Google Scholar Back to article
S. Haykin, “Neural Network: A Comprehensive Foundation”, Prentice Hall, 1994.
Search in Google Scholar Back to article
A Tyagi et al., “A Low-Cost Portable Temperature-Moisture Sensing Unit With Artificial Neural Network Based Signal Conditioning For Smart Irrigation Applications”, in International Journal on Smart Sensing and Intelligent Systems, Vol. 4, No. 1, pp 94-111, Mar 2011.10.21307/ijssis-2017-428
Search in Google Scholar Back to article
L. Gatet et al., “Integrated CMOS analog neural network ability to linearise the distorted characteristic of HPA embedded in satellites”, in 4th IEEE International Workshop on Electronic Design, Test and Applications (DELTA 2008), Hong Kong, pp. 502-505, Jan. 23-25, 2008.10.1109/DELTA.2008.49
Search in Google Scholar Back to article
D. Roviras et al., “Multi-Layer Perceptron Neural Network Implementation and Integration in CMOS Technology”, in International Conference on Information and Communications Technologies: From Theory to Application (ICCTA 94), Damascus, Syria, pp. 19-23, April 2004.
Search in Google Scholar Back to article
L. Gatet et al., “Embedded updating system based on integrated NNs in order to achieve adaptative predistortion of non-linear HPA characteristics”, in 26th IEEE International Instrumentation and Measurement Technology Conference (I2MTC 2009), Singapore, pp. 838841, May 5-7, 2009.
Search in Google Scholar Back to article
L. Gatet et al., “Functional Tests of a 0.6μm CMOS MLP Analog Neural Network for Fast on-board Signal Processing”, in Analog Integrated Circuits and Signal Processing, Springer Science & Business Media, Vol. 54, No. 3, pp. 219-227, March 2008.10.1007/s10470-008-9133-5
Search in Google Scholar Back to article
L. Gatet et al., “Design and Test of a CMOS MLP Analog Neural Network for Fast OnBoard Signal Processin”, in 13th IEEE International Conference on Electronics, Circuits and Systems, Nice, France, pp. 922-925, Dec. 2006.10.1109/ICECS.2006.379940
Search in Google Scholar Back to article
L. Gatet et al., “Real-Time Surface Discrimination Using an Analog Neural Network Implemented in a Phase-Shift Laser Rangefinder”, in IEEE Sensors Journal, Vol. 7, No. 10, pp. 1381-1387, Oct. 2007.
Search in Google Scholar Back to article
B. Mulliez et al., “Predistortion System Implementation Based On Analog Neural Networks For Linearizing High Power Amplifiers Transfer Characteristics”, in 36th International Conference on Telecommunication and Signal Processing (TSP 2013), Rome, pp 412-416, July 2-4, 2013.10.1109/TSP.2013.6613964
Search in Google Scholar Back to article
A. Uncini et al., “Complex-Valued Neural Networks with Adaptive Spline Activation Function for Digital Radio Links Nonlinear Equalization”, in IEEE Trans. Signal Processing, Vol. 47, pp. 505-514, Feb 1999.10.1109/78.740133
Search in Google Scholar Back to article

Predistortion System Implementation Based On Analog Neural Networks For Linearizing High Power Amplifiers Transfer Characteristics

Abstract

Paradigm

My account