L.I. Averina1, N. E. Guterman2

1,2 JSC «Concern «Sozvezdie» (Voronezh, Russia)

1 averina@phys.vsu.ru; 2 n.guterman@internet.ru

One of the most important parts of modern wireless communication systems is a digital predistortion technology, which servers to eliminate nonlinear distortions introduced by wideband power amplifiers. Widespread learning architectures used in practice have a number of disadvantages. Direct Learning Architecture (DLA) has a good accuracy and reasonable stability at low signal to noise ratio, but it is burdened with high computational complexity. Another significant drawback is related to requirement in power amplifier modeling, which in practice leads to sensible loss of accuracy. Simpler approach named Indirect Learning Architecture (ILA) is easy to implement in hardware, but it also carries unavoidable shortcomings. Estimator, which is generated for digital predistorter parameters, converges to a biased solution and its bias is proportional to noise variance. An alternative approach proposed not so long ago originates in the theory of optimal control and is called Iterative Learning Control (ILC). This method differs from those described above in that it allows obtaining optimal input signal of power amplifier. Such generated waveform passed through nonlinear element will give an amplified input signal of transmitter path. ILC eliminates disadvantages of two widespread learning architectures due to implementation simplicity and noise immunity. Comparative analysis conducted in this article fully proves above statements.

Averina L.I., Guterman N.E. Comparative analysis of learning architectures for digital predistortion in wideband power amplifier linearization task. Radiotekhnika. 2025. V. 89. № 9. P. 45−53. DOI: https://doi.org/10.18127/j00338486-202509-04 (In Russian)

1. Cripps S.C. RF power amplifiers for wireless communications. 2nd ed. Boston: Artech House. 2006. 456 p.
2. Eun C., Powers E.J. A new Volterra predistorter based on the indirect learning architecture. IEEE Transactions on Signal Processing. 1997. V. 45, № 1. P. 223-227.
3. Ding L., Zhou G.T., Morgan D.R., et al. A robust digital baseband predistorter constructed using memory polynomials. IEEE Transactions on Communications. 2004. V. 52. № 1. Р. 159-165.
4. Morgan D.R., Ma Z., Ding L. Reducing measurement noise effects in digital predistortion of RF power amplifiers. IEEE Int. Conf. on Communications. Anchorage. N.Y. AK. USA. IEEE. 2003. Р. 2436-2439.
5. Zhou D., DeBrunner V.E. Novel adaptive nonlinear predistorters based on the direct learning algorithm. IEEE Transactions on Signal Processing. 2007. V. 55. № 1. Р. 120-133.
6. Jardel O., De Groote F., Reveyrand T. An Electrothermal model for AlGaN/GaN power HEMTs including trapping effects to improve large-signal simulation results on high VSWR. IEEE Transactions on Microwave Theory and Techniques. 2007. V. 55. № 12. Р. 2660-2669.
7. Chani-Cahuana J., Landin P. N., Fager C., Eriksson T. Iterative learning control for RF power amplifier linearization. IEEE Transactions on Microwave Theory and Techniques. 2016. V. 64. № 9. Р. 2778-2789.
8. Bristow D.A., Tharayil M., Alleyne A.G. A survey of iterative learning control. IEEE Control Systems Magazine. 2006. V. 26. № 3. Р. 96-114.
9. Kim J., Konstantinou K. Digital predistortion of wideband signals based on power amplifier model with memory. Electronics Letters. 2001. V. 37. № 23. Р. 1417-1418.
10. Morgan D.R., Ma Z., Kim J., et al. A generalized memory polynomial model for digital predistortion of RF power amplifiers. IEEE Transactions on Signal Processing. 2006. V. 54. № 10. Р. 3852-3860.
11. Zhu A., Pedro J.C., Brazil T.J. Dynamic deviation reduction-based volterra behavioral modeling of RF power amplifiers. IEEE Transactions on Microwave Theory and Techniques. 2006. V. 54. № 12. Р. 4323-4332.
12. Zhu A. Decomposed vector rotation-based behavioral modeling for digital predistortion of RF power amplifiers. IEEE Transactions on Microwave Theory and Techniques. 2015. V. 63. № 2. Р. 737-744.
13. Crespo-Cadenas C., Madero-Ayora M.J., Becerra J.A. A bivariate Volterra series approach to modeling and linearization of power amplifiers. 2021 IEEE Topical Conference on RF/Microwave Power Amplifiers for Radio and Wireless Applications (PAWR). San Diego. CA. USA. IEEE. 2021. Р. 4-7.
14. Hayes M.H. Statistical Digital Signal Processing and Modeling. Toronto: John Wiley & Sons, Inc. 1997. 608 p.
15. Guo C., Poletti D. Scheme for automatic differentiation of complex loss functions with applications in quantum physics. Physical Review E. 2021. V. 103. № 1. Р. 9.
16. Fawzy A., Sun S., Lim T.J., et al. Iterative learning control based digital pre-distortion for mitigating impairments in MIMO wireless transmitters. IEEE Transactions on Vehicular Technology. 2023. V. 72. № 6. Р. 6933-6947.
17. Ghannouchi F.M., Hammi O., Helaoui M. Behavioral modeling and predistortion of wideband wireless transmitters. Chichester: John Wiley & Sons, Ltd. 2015. 253 p.
18. Park S.H. Collinearity and optimal restrictions on regression parameters for estimating responses. Technometrics. 1981. V. 23. № 3. Р. 289-295.