Dimensioning an FPGA for Real-Time Implementation of State of the Art Neural Network-Based HPA Predistorter

Orthogonal Frequency Division Multiplexing (OFDM) is one of the key modulations for current and novel broadband communications standards. For example, Multi-band Orthogonal Frequency Division Multiplexing (MB-OFDM) is an excellent choice for the ECMA-368 Ultra Wideband (UWB) wireless communication standard. Nevertheless, the high Peak to Average Power Ratio (PAPR) of MB-OFDM UWB signals reduces the power efficiency of the key element in mobile devices, the High Power Amplifier (HPA), due to non-linear distortion, known as the non-linear saturation of the HPA. In order to deal with this limiting problem, a new and efficient pre-distorter scheme using a Neural Networks (NN) is proposed and also implemented on Field Programmable Gate Array (FPGA). This solution based on the pre-distortion concept of HPA non-linearities offers a good trade-off between complexity and performance. Some tests and validation have been conducted on the two types of HPA: Travelling Wave Tube Amplifiers (TWTA) and Solid State Power Amplifiers (SSPA). The results show that the proposed pre-distorter design presents low complexity and low error rate. Indeed, the implemented architecture uses 10% of DSP (Digital Signal Processing) blocks and 1% of LUTs (Look up Table) in case of SSPA, whereas it only uses 1% of LUTs in case of TWTA. In addition, it allows us to conclude that advanced machine learning techniques can be efficiently implemented in hardware with the adequate design.

[1]  Abdel Magid Hamouda,et al.  Bandwidth Enhancement and Frequency Scanning Array Antenna Using Novel UWB Filter Integration Technique for OFDM UWB Radar Applications in Wireless Vital Signs Monitoring , 2018, Sensors.

[2]  Li Li,et al.  FPGA Implementation of a BPSK 1D-CNN Demodulator , 2018 .

[3]  J.A.C. Bingham,et al.  Multicarrier modulation for data transmission: an idea whose time has come , 1990, IEEE Communications Magazine.

[4]  Jean-Bernard Rault,et al.  OFDM for digital TV broadcasting , 1994, Signal Process..

[5]  Min Zhang,et al.  Enhanced Efficiency BPSK Demodulator Based on One-Dimensional Convolutional Neural Network , 2018, IEEE Access.

[6]  Christian Lüders,et al.  Theory and Applications of OFDM and CDMA: Wideband Wireless Communications , 2005 .

[7]  Víctor P. Gil Jiménez,et al.  Practical Guidelines for Approaching the Implementation of Neural Networks on FPGA for PAPR Reduction in Vehicular Networks , 2018, Sensors.

[8]  R. Duren,et al.  A comparison of FPGA and DSP development environments and performance for acoustic array processing , 2007, 2007 50th Midwest Symposium on Circuits and Systems.

[9]  Wirawan,et al.  Nonlinear Distortion Cancellation using Predistorter in MIMO-GFDM Systems , 2019, Electronics.

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

[11]  Sven-Gustav Häggman,et al.  New aspects on nonlinear power amplifier modeling in radio communication system simulations , 1997, Proceedings of 8th International Symposium on Personal, Indoor and Mobile Radio Communications - PIMRC '97.

[12]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[13]  Mukul Shirvaikar,et al.  A comparison between DSP and FPGA platforms for real-time imaging applications , 2009, Electronic Imaging.

[14]  Víctor P. Gil Jiménez,et al.  High Power Amplifier Pre-Distorter Based on Neural-Fuzzy Systems for OFDM Signals , 2011, IEEE Transactions on Broadcasting.

[15]  Ryuji Kohno,et al.  A Novel UWB Pulse Shape Modulation System , 2002, Wirel. Pers. Commun..

[16]  Susmita Das,et al.  A comparison between MLP NN and RBF NN techniques for the detection of stator inter-turn fault of an induction motor , 2010, 2010 International Conference on Industrial Electronics, Control and Robotics.

[17]  Abdellah Ait Ouahman,et al.  Reduction of Power Fluctuation in ECMA-368 Ultra Wideband Communication Systems Using Multilayer Perceptron Neural Networks , 2013, Wireless Personal Communications.

[18]  Chung Gu Kang,et al.  BER analysis of dual-carrier modulation (DCM) over Rayleigh fading channel , 2010, International Congress on Ultra Modern Telecommunications and Control Systems.

[19]  V. G. Krizhanovski,et al.  Advanced Design Techniques for RF Power Amplifiers , 2006 .

[20]  Kerri L. Cahoy,et al.  Communication satellite power amplifiers: current and future SSPA and TWTA technologies , 2016, Int. J. Satell. Commun. Netw..

[21]  Rocco Fazzolari,et al.  A Reinforcement Learning-Based QAM/PSK Symbol Synchronizer , 2019, IEEE Access.

[22]  Abdelhamid Louliej,et al.  Design and FPGA implementation of a new approximation for PAPR reduction , 2018 .

[23]  Olav Tirkkonen,et al.  On the Waveforms for 5G Mobile Broadband Communications , 2015, 2015 IEEE 81st Vehicular Technology Conference (VTC Spring).

[24]  Abu B. Sesay,et al.  Adaptive asymmetric linearization of radio over fiber links for wireless access , 2002, IEEE Trans. Veh. Technol..

[25]  Hyosung Nam,et al.  A 2.4 GHz 20 W 8-channel RF Source Module with Solid-State Power Amplifiers for Plasma Generators , 2020 .

[26]  Chintha Tellambura,et al.  SLM and PTS peak-power reduction of OFDM signals without side information , 2005, IEEE Transactions on Wireless Communications.

[27]  Cesar A. Azurdia-Meza,et al.  OFDM: today and in the future of next generation wireless communications , 2016, 2016 IEEE Central America and Panama Student Conference (CONESCAPAN).

[28]  Douglas L. Jones,et al.  PAR reduction in OFDM via active constellation extension , 2003, IEEE Trans. Broadcast..