volume | PIER Journals

Abstract

Neural networks have become a focal point for their ability to effectively capture the complex nonlinear characteristics of power amplifiers (PAs) and facilitate the design of digital predistortion (DPD) circuits. This is accomplished through the utilization of nonlinear activation functions (AFs) that are the cornerstone in a neural network architecture. In this paper, we delve into the influence of eight carefully selected AFs on the performance of the neural network–based DPD. We particularly explore their interaction with both the depth and width of the neural network. In addition, we provide an extensive performance analysis using two crucial metrics: the normalized mean square error (NMSE) and the adjacent channel power ratio (ACPR). Our findings highlight the superiority of the exponential linear unit activation function (ELU AF), particularly within deep neural network (DNN) frameworks, among the AFs under consideration.

1. Mohammady, Somayeh, Ronan Farrell, David Malone, and John Dooley, "Performance investigation of peak shrinking and interpolating the PAPR reduction technique for LTE-advance and 5G signals," Information, Vol. 11, No. 1, 20, 2019.

2. Lopez-Bueno, David, Teng Wang, Pere L. Gilabert, and Gabriel Montoro, "Amping up, saving power: Digital predistortion linearization strategies for power amplifiers under wideband 4G/5G burst-like waveform operation," IEEE Microwave Magazine, Vol. 17, No. 1, 79-87, 2015.

3. Wood, John, Behavioral Modeling and Linearization of RF Power Amplifiers, Artech House, Boston; London, 2014.

4. Ceylan, Nazim, J.-E. Mueller, and Robert Weigel, "Optimization of EDGE terminal power amplifiers using memoryless digital predistortion," IEEE Transactions on Microwave Theory and Techniques, Vol. 53, No. 2, 515-522, 2005.

5. Kim, Jaehyeong and K. Konstantinou, "Digital predistortion of wideband signals based on power amplifier model with memory," Electronics Letters, Vol. 37, No. 23, 1417–1418, 2001.

6. Zhu, Anding, Jos C. Pedro, and Thomas J. Brazil, "Dynamic deviation reduction-based Volterra behavioral modeling of RF power amplifiers," IEEE Transactions on Microwave Theory and Techniques, Vol. 54, No. 12, 4323-4332, 2006.

7. Morgan, Dennis R., Zhengxiang Ma, Jaehyeong Kim, Michael G. Zierdt, and John Pastalan, "A generalized memory polynomial model for digital predistortion of RF power amplifiers," IEEE Transactions on Signal Processing, Vol. 54, No. 10, 3852-3860, 2006.

8. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton, "Deep learning," Nature, Vol. 521, No. 7553, 436-444, 2015.
doi:10.1038/nature14539

9. Wang, Yingying, Yibin Li, Yong Song, and Xuewen Rong, "The influence of the activation function in a convolution neural network model of facial expression recognition," Applied Sciences, Vol. 10, No. 5, 1897, 2020.

10. Liew, Shan Sung, Mohamed Khalil-Hani, and Rabia Bakhteri, "Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems," Neurocomputing, Vol. 216, 718-734, 2016.

11. Pedamonti, Dabal, "Comparison of non-linear activation functions for deep neural networks on MNIST classification task," ArXiv Preprint ArXiv:1804.02763, 2018.

12. Wang, Dongming, Mohsin Aziz, Mohamed Helaoui, and Fadhel M. Ghannouchi, "Augmented real-valued time-delay neural network for compensation of distortions and impairments in wireless transmitters," IEEE Transactions on Neural Networks and Learning Systems, Vol. 30, No. 1, 242-254, 2018.

13. Hongyo, Reina, Yoshimasa Egashira, Thomas M. Hone, and Keiichi Yamaguchi, "Deep neural network-based digital predistorter for Doherty power amplifiers," IEEE Microwave and Wireless Components Letters, Vol. 29, No. 2, 146-148, 2019.

14. Yu, Xiaoqi, Xiaohu Fang, Jie Shi, Guangsheng Lv, Changning Wei, and Jiangwei Sui, "Deep neural network based stable digital predistortion using ELU activation for switchless class-G power amplifier," 2024 IEEE MTT-S International Wireless Symposium (IWS), 1-3, Beijing, China, 2024.

15. Jiang, Yiyue, Andrius Vaicaitis, John Dooley, and Miriam Leeser, "Efficient neural networks on the edge with FPGAs by optimizing an adaptive activation function," Sensors, Vol. 24, No. 6, 1829, 2024.
doi:10.3390/s24061829

16. Filicori, F. and G. Vannini, "Mathematical approach to large-signal modelling of electron devices," Electronics Letters, Vol. 27, No. 4, 357-359, 1991.
doi:10.1049/el:19910226

17. Gilabert, Pere L. and Gabriel Montoro, "Look-up table implementation of a slow envelope dependent digital predistorter for envelope tracking power amplifiers," IEEE Microwave and Wireless Components Letters, Vol. 22, No. 2, 97-99, 2012.

18. Fischer-Bühner, Arne, Lauri Anttila, Manil Dev Gomony, and Mikko Valkama, "Phase-normalized neural network for linearization of RF power amplifiers," IEEE Microwave and Wireless Technology Letters, Vol. 33, No. 9, 1357-1360, 2023.

19. Lima, Eduardo G., Telmo R. Cunha, and José C. Pedro, "A physically meaningful neural network behavioral model for wireless transmitters exhibiting PM-AM/PM-PM distortions," IEEE Transactions on Microwave Theory and Techniques, Vol. 59, No. 12, 3512-3521, 2011.

20. Zhang, Yikang, Yue Li, Falin Liu, and Anding Zhu, "Vector decomposition based time-delay neural network behavioral model for digital predistortion of RF power amplifiers," IEEE Access, Vol. 7, 91559-91568, 2019.

21. Bawa, Vivek Singh and Vinay Kumar, "Linearized sigmoidal activation: A novel activation function with tractable non-linear characteristics to boost representation capability," Expert Systems with Applications, Vol. 120, 346-356, 2019.

22. Lohani, Harshit Kumar, S. Dhanalakshmi, and V. Hemalatha, "Performance analysis of extreme learning machine variants with varying intermediate nodes and different activation functions," Cognitive Informatics and Soft Computing: Proceeding of CISC 2017, 613-623, 2019.

23. Koçak, Yılmaz and Gülesen Üstündağ Şiray, "New activation functions for single layer feedforward neural network," Expert Systems with Applications, Vol. 164, 113977, 2021.

24. Nair, Vinod and Geoffrey E. Hinton, "Rectified linear units improve restricted boltzmann machines," Proceedings of the 27th International Conference on Machine Learning (ICML-10), 807-814, 2010.

25. Trottier, Ludovic, Philippe Giguere, and Brahim Chaib-Draa, "Parametric exponential linear unit for deep convolutional neural networks," 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), 207-214, Cancun, Mexico, 2017.

26. Hendrycks, Dan and Kevin Gimpel, "Gaussian error linear units (GELUS)," ArXiv Preprint ArXiv:1606.08415, 2016.

27. Ramachandran, Prajit, Barret Zoph, and Quoc V. Le, "Searching for activation functions," ArXiv Preprint ArXiv:1710.05941, 2017.

28. MathWorks "Power amplifier characterization," https://www.mathworks.com/help/comm/ug/power-amplifier-characterization.html, June 2024.

29. Fawzy, Abdelwahab, Sumei Sun, Teng Joon Lim, and Yong Xin Guo, "An efficient deep neural network structure for RF power amplifier linearization," 2021 IEEE Global Communications Conference (GLOBECOM), 1-6, Madrid, Spain, 2021.

Dr. Mostapha Ouadefli

Dr. Mohamed Et-tolba

Professor Abdelwahed Tribak

Dr. Tomas Fernandez Ibanez