Advertisement

Comparison of a genetic programming approach with ANFIS for power amplifier behavioral modeling and FPGA implementation

  • José Alejandro Galaviz-Aguilar
  • Patrick Roblin
  • José Ricardo Cárdenas-Valdez
  • Emigdio Z-Flores
  • Leonardo Trujillo
  • José Cruz Nuñez-Pérez
  • Oliver Schütze
Methodologies and Application
  • 179 Downloads

Abstract

Accurate modeling of power amplifiers (PA) is of upmost importance in the design process of wireless communication systems where a high linearity and efficiency is required. To deal with the nonlinear behavior of PAs effectively a linearization stage is applied to minimize the distortions of in-band and adjacent transmission channels, which translate to an improvement of the signal integrity and the operation cost of the transmitter system. This paper presents a method based on genetic programming with a local search heuristic (GP-LS) to emulate the electrical memory effects by using the characteristic conversion curves of the radio frequency (RF) PA NXP Semiconductor of 10 W GaN HEMT working at 2.34 GHz. This method is compared with an Adaptive Neuro-Fuzzy Inference Systems (ANFIS) through several performance metrics (NMSE, MAE and correlation coefficient), with GP-LS achieving a better modeling accuracy. Moreover, the models produced by GP-LS permit a reduction in the required hardware resources, when it is implemented on a Field-Programmable Gate Array through the DSP Builder tool. The models are derived using a data-driven approach, posed in two different ways. Firstly, experiments are performed using a testbed Arria V GX for a flexible vector signal generation that provides the raw data of the PA characterization using an LTE-Advanced signal with 10-MHz bandwidth. Secondly, the modeling is derived from a filtered version of the data and then adding a high-frequency signal as a post processing step to approximate the true behavior of the system. In both cases, the models are generated with ANFIS and GP-LS, performing extensive logic-based simulations and implementing the models on a Cyclone III development board. Both approaches are compared based on accuracy and required hardware resources, with GP-LS substantially outperforming ANFIS. These results suggest that the GP-LS models can be implemented in a digital predistortion chain and used in the linearization stage for a RF-PA.

Keywords

ANFIS Digital predistortion Genetic programming Linearization Power amplifier modeling Radio frequency 

Notes

Acknowledgements

The authors would like to express their gratitude to the IPN for its financial support by the Project “SIP-20170588”. Funding for this work was also provided by CONACYT (Mexico) Basic Science Research Project No. 178323, the FP7-Marie Curie-IRSES 2013 European Commission program through project ACoBSEC with contract No. 612689, and CONACYT Project FC-2015-2/944 “Aprendizaje evolutivo a gran escala”. Finally, first and fourth author were, respectively, supported by CONACYT scholarships Nos. 385469 and 294213.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Akkaya E (2016) ANFIS based prediction model for biomass heating value using proximate analysis components. Sci Technol Fuel Energy 180:687–693.  https://doi.org/10.1016/j.fuel.2016.04.112 Google Scholar
  2. Amin S, Van Moer W, Handel P, Ronnow D (2015) Characterization of concurrent dual-band power amplifiers using a dual two-tone excitation signal. IEEE Trans Instrum Meas 64(10):2781–2791.  https://doi.org/10.1109/TIM.2015.2427731 CrossRefGoogle Scholar
  3. Anding Z, Brazil TJ (2014) Behavioral modeling of RF power amplifiers based on pruned volterra series. IEEE Microw Wirel Compon Lett 14(12):563–565.  https://doi.org/10.1109/LMWC.2004.837380 Google Scholar
  4. Boumaiza S, Helaoui M, Hammi O, Liu T, Ghannouchi FM (2007) Systematic and adaptive characterization approach for behavior modeling and correction of dynamic nonlinear transmitters. IEEE Trans Instrum Meas 56(6):2203–2211.  https://doi.org/10.1109/TIM.2007.908600 CrossRefGoogle Scholar
  5. Castelli M, Vanneschi L, Silva S (2013) Prediction of high performance concrete strength using genetic programming with geometric semantic genetic operators. Expert Syst Appl 40(17):6856–6862.  https://doi.org/10.1016/j.eswa.2013.06.037 CrossRefGoogle Scholar
  6. Castelli M, Vanneschi L, Silva S (2014) Prediction of the Unified Parkinson’s disease rating scale assessment using a genetic programming system with geometric semantic genetic operators. Expert Syst Appl 41(10):4608–4616.  https://doi.org/10.1016/j.eswa.2014.01.018 CrossRefGoogle Scholar
  7. Galaviz-Aguilar JA, Chang HC, Martinez-Rodriguez F, Roblin P, Nunez-Perez JC (2016) Measurement of dynamic power dissipation and estimation of effective dynamic efficiencies in an LTE Chireix PA. In: 88th ARFTG microwave measurement conference (ARFTG), Austin, TX, pp 1–4Google Scholar
  8. Gao F, Lee T, Cao W, Lee X, Deng Y, Tong H (2016) Self-evolution of hyper fractional order chaos driven by a novel approach through genetic programming. Expert Syst Appl 52:1–15.  https://doi.org/10.1016/j.eswa.2015.12.033 CrossRefGoogle Scholar
  9. García P, Mingo J, Carro P, Valdovinos A (2010) Efficient feedforward linearization technique using genetic algorithms for OFDM systems. EURASIP J Adv Signal Process 2010(1):354030.  https://doi.org/10.1155/2010/354030 zbMATHGoogle Scholar
  10. Hosseini MS, Zekri M (2012) Review of medical image classification using the adaptive neuro-fuzzy inference system. J Med Signals Sens 2(1):49–60Google Scholar
  11. Jang JR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence, vol 1. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  12. Javad M, Shahkari A, Shokouhi B (2013) A review of intelligent predistortion methods for the linearization of RF power amplifiers. In: International conference on computer applications technology, Sousse, Tunisia, pp 1–6Google Scholar
  13. Jianfeng Z, Jianyi Z, Lei Z, Jianing Z, Wei H (2008) ANFIS implementation in FPGA for power amplifier linearization with digital predistortion. In: International conference microwave and millimeter wave technology, Nanjing, pp 1474–1476Google Scholar
  14. Junghwan M, Saad, O, Jungwan, S, Fager, C, Bumman K (2012) 2-D enhanced hammerstein behavior model for concurrent dual-band power amplifiers. In: European microwave conference, Amsterdam, pp 869–872Google Scholar
  15. Kommenda M, Kronberger G, Winkler S, Affenzeller M, Wagner S (2013) Effects of constant optimization by nonlinear least squares minimization in symbolic regression. In: Proceedings of the 15th annual conference companion on genetic and evolutionary computation, ACM, New York, pp 1121-1128Google Scholar
  16. Koza JR (1992) Genetic programming: On the programming of computers by means of natural selection. MIT Press, CambridgezbMATHGoogle Scholar
  17. Koza JR (2010) Human-competitive results produced by genetic programming. Genet Program Evolv Mach 11(3):251–284.  https://doi.org/10.1007/s10710-010-9112-3 CrossRefGoogle Scholar
  18. Langdon WB, Poli R (2002) Foundations of genetic programming. Springer, New YorkCrossRefzbMATHGoogle Scholar
  19. Lee KC, Gardner P (2006) Adaptive neuro-fuzzy inference system (ANFIS) digital predistorter for RF power amplifier linearization. IEEE Trans Veh Technol 55(1):43–51.  https://doi.org/10.1109/TVT.2005.861171 CrossRefGoogle Scholar
  20. Liao H (2012) A digital predistortion theory based on self-adaptive algorithm. J Theor Appl Inf Technol 45(2):515–519Google Scholar
  21. Mišić J, Marković V, Marinkovic Z (2014) Volterra kernels extraction from neural networks for amplifier behavioral modeling. In: International symposium on telecommunications, Sarajevo, pp 1–6Google Scholar
  22. Mitra S, Hayashi Y (2000) Neuro-fuzzy rule generation: survey in soft computing framework. IEEE Trans Neural Netw 11(3):748–768.  https://doi.org/10.1109/72.846746 CrossRefGoogle Scholar
  23. Mohammadi K, Shamshirband S, Kamsin A, Zulkefli M (2016) Identifying the most significant input parameters for predicting global solar radiation using an ANFIS selection procedure. Renew Sustain Energy Rev 63:423–434.  https://doi.org/10.1016/j.rser.2016.05.065 CrossRefGoogle Scholar
  24. Mondal R, Ristaniemi T, Doula M (2013) Genetic algorithm optimized memory polynomial digital pre-distorter for RF power amplifiers. In: International conference on wireless communications and signal processing, Hangzhou, pp 1–5Google Scholar
  25. Montaña J, Alonso C, Borges C, Tîrnăucă C (2016) Model-driven regularization approach to straight line program genetic programming. Expert Syst Appl 57:76–90.  https://doi.org/10.1016/j.eswa.2016.03.003 CrossRefGoogle Scholar
  26. Naraharisetti N, Roblin P, Quindroit C, Rawat M, Gheitanchi S (2013) Quasi-exact inverse PA model for digital predistorter linearization. In: 82nd ARFTG in microwave measurement conference, Columbus, OH, pp 1–4Google Scholar
  27. O’Droma M, Meza S, Yiming L (2009) New modified saleh models for memoryless nonlinear power amplifier behavioural modelling. IEEE Commu Lett 13(6):399–401.  https://doi.org/10.1109/LCOMM.2009.090222 CrossRefGoogle Scholar
  28. Ping-hui L, Peng W (2010) Wiener-Saleh modeling of nonlinear RF power amplifiers considering memory effects. In: 2010 international conference on microwave and millimeter wave technology, Chengdu, pp 1447–1449Google Scholar
  29. Poli R, Langdon W, McPhee N (2008) A field guide to genetic programming. Lulu Enterprises, LondonGoogle Scholar
  30. Samarjit K, Sujit D, Pijush K (2014) Applications of neuro fuzzy systems: a brief review and future outline. Appl Soft Comput 15:243–259.  https://doi.org/10.1016/j.asoc.2013.10.014 CrossRefGoogle Scholar
  31. Sen S, Devarakond SK, Chetterjee A (2010) DSP assisted low cost IQ mismatch measurement and compensation using built in power detector. In: IEEE MTT-S international microwave symposium digest (MTT), Anaheim, USA, pp 336–339Google Scholar
  32. Sills JA, Sperling R (2002) Adaptive power amplifier linearization by digital pre-distortion using genetic algorithms. In: Proceedings of IEEE radio and wireless conference RAWCON, Boston, Massachusetts, USA, pp 229–232Google Scholar
  33. Silva S, Costa E (2009) Dynamic limits for bloat control in genetic programming and a review of past and current bloat theories. Genet Program Evolv Mach 10(2):141–179.  https://doi.org/10.1007/s10710-008-9075-9 CrossRefGoogle Scholar
  34. Sperlich R, Sills JA, Kenney JS (2005) Closed-loop digital pre-distortion with memory effects using genetic algorithms. In: IEEE MTT-S international microwave symposium digest, Long Beach, CA, p 4Google Scholar
  35. Staudinger J, Nanan J, Wood J (2010) Memory Fading Volterra series model for high power infrastructure amplifiers. In: IEEE Radio and wireless symposium, New Orleans, LA, pp 184–187Google Scholar
  36. Trujillo L, Legrand P, Olague G, Lévy-Véhel J (2012) Evolving estimators of the pointwise Hölder exponent with genetic programming. Inf Sci 209:61–79.  https://doi.org/10.1016/j.ins.2012.04.043 CrossRefGoogle Scholar
  37. Weiß M (2000) Measuring the dynamic characteristic of high-frequency amplifiers with real signals. In: European wireless. Dresden, Germany, pp 67–71Google Scholar
  38. Wisell DH, Rudlund B, Ronnow D (2007) Characterization of memory effects in power amplifiers using digital two-tone measurements. IEEE Trans Instrum Meas 56(6):2757–2766.  https://doi.org/10.1109/TIM.2007.907949 CrossRefGoogle Scholar
  39. Z-Flores E, Trujillo L, Schütze O, Legrand P (2014) Evaluating the effects of local search in genetic programming. In: Tantar AA, et al (eds) EVOLVE—a bridge between probability, set oriented numerics, and evolutionary computation V, Springer, Berlin, no. 288 in Advances in Intelligent Systems and Computing, pp 213–228Google Scholar
  40. Z-Flores E, Trujillo L, Schütze O, Legrand P (2015) A local search approach to genetic programming for binary classification. In: Proceedings of the genetic and evolutionary computation conference, GECCO 2015, Madrid, Spain, pp 1151–1158Google Scholar
  41. Zhai J, Zhou J, Zhang L, Zhao J, Hong W (2009) The dynamic behavioral model of RF power amplifiers with the modified ANFIS. IEEE Trans Microw Theory Tech 57(1):27–35.  https://doi.org/10.1109/TMTT.2008.2009085 CrossRefGoogle Scholar
  42. Zhai J, Zhou J, Zhang L, Hong W (2010) Behavioral modelling of power amplifiers with dynamic fuzzy neural network. IEEE Microw Wirel Compon Lett 20(9):528–530.  https://doi.org/10.1109/LMWC.2010.2052594 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  • José Alejandro Galaviz-Aguilar
    • 1
    • 2
  • Patrick Roblin
    • 2
  • José Ricardo Cárdenas-Valdez
    • 3
  • Emigdio Z-Flores
    • 3
  • Leonardo Trujillo
    • 3
  • José Cruz Nuñez-Pérez
    • 1
  • Oliver Schütze
    • 4
  1. 1.Instituto Politécnico Nacional, IPN-CITEDITijuanaMexico
  2. 2.Department of Electrical and Computer EngineeringThe Ohio State UniversityColumbusUSA
  3. 3.Posgrado en Ciencias de la Ingeniería, Departamento de Ingeniería Eléctrica y ElectrónicaInstituto Tecnológico de TijuanaTijuanaMexico
  4. 4.Cinvestav-IPNComputer Science DepartmentMexicoMexico

Personalised recommendations