A Power Amplifier Modeling Method Based on the Time Delay Deep Neural Network
DOI:
https://doi.org/10.53469/jrse.2025.07(01).16Keywords:
Time delay deep neural network, Power amplifier modeling, Multi-layer networkAbstract
A power amplifier (PA) modeling method based on the time delay deep neural network (TDDNN) is proposed in this paper. By integrating time-delay units with a multi-layer hidden neural network structure, the TDDNN enhances the modeling capability for dynamic nonlinear systems. Time-delay information and a multi-layer network architecture are incorporated into the TDDNN to improve its ability to capture the memory effects and nonlinear characteristics of input signals, thereby increasing modeling accuracy. Meanwhile, the number of hidden layer neurons in TDDNN is reduced, which optimizes the structural complexity of the model. The feasibility of this innovative structure is demonstrated through a case study of a Motorola PA. Experimental validation indicates that the proposed TDDNN method not only improves modeling accuracy but also effectively reduces computational complexity, offering an efficient solution for modeling complex dynamic nonlinear systems.
References
J. Li, L. Peng, Z. Zhang and G. Zhang (2023). A mm-Wave Parallel-Combined Power Amplifier Supporting Balanced/Unbalanced Mode for 5G NR FR2 Applications. IEEE Microwave and Wireless Technology Letters, vol. 33, no. 5, p. 543-546.
S. Sakata et al (2022). A 3.4-4.1GHz Broadband GaN Doherty Power Amplifier Module for 5G massive-MIMO Base-Stations. 2022 Asia-Pacific Microwave Conference (APMC), p. 500-502.
H.F. Wu, Q.F. Cheng, S.X. Yan, Q.J. Zhang and J.G. Ma (2015). Transistor Model Building for a Microwave Power Heterojunction Bipolar Transistor. IEEE Microwave Magazine, vol. 16, no. 2, p. 85-92.
K. Han, Z. Liu, X. Hu and W. Wang (2021). Filter-free Band-limited Digital Predistortion of Power Amplifiers for 5G Wireless Transmitters. 2021 Photonics & Electromagnetics Research Symposium (PIERS), p. 1876-1888.
F. M. Yigletu, B. Iñiguez, S. Khandelwal and T. A. Fjeldly (2013). A compact charge-based physical model for AlGaN/GaN HEMTs. 2013 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems, p. 97-99.
H. Gao H, A. Zhang, J. Jin (2020). RF modeling and parameter extraction for GaAs-based on-chip inductors. Microw Opt Technol Lett. Vol. 62, pp. 1930–1934.
Q.H. Le, D.K. Huynh, S. Lehmann, Z. Zhao, T. Kämpfe and M. Rudolph (2021). Empirical Large-Signal Modeling of mm-Wave FDSOI CMOS Based on Angelov Model. IEEE Transactions on Electron Devices, vol. 68, no. 4, p. 1446-1453.
P. Chandra et al (2021). Rapid LUT Modelling Technique for GaN HEMT Based MMIC Technology. 2021 IEEE MTT-S International Microwave and RF Conference (IMARC), p. 1-4.
Y.L. Yang, and C.X. Li (2021). Quantitative Analysis of the Generalization Ability of Deep Feedforward Neural Networks. Journal of Intelligent & Fuzzy Systems, vol. 40, no. 3, p. 4867 – 4876.
C. Zhang, S. Yan, Q.J. Zhang and J.G. Ma (2013). Behavioral modeling of power amplifier with long term memory effects using recurrent neural networks. 2013 IEEE International Wireless Symposium (IWS), p. 1-4.
C. Jiang et al (2022). Block-Oriented Time-Delay Neural Network Behavioral Model for Digital Predistortion of RF Power Amplifiers. IEEE Transactions on Microwave Theory and Techniques, vol. 70, no. 3, p. 1461-1473.
D. Snyder, D. Garcia-Romero and D. Povey (2015). Time delay deep neural network-based universal background models for speaker recognition. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), p. 92-97.
D. Wang, M. Aziz, M. Helaoui, and F. M. Ghannouchi (2019). 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, p. 242–254.
Y. Zhang, Y. Li, F. Liu and A. Zhu (2019). Vector Decomposition Based Time-Delay Neural Network Behavioral Model for Digital Predistortion of RF Power Amplifiers. IEEE Access, vol. 7, p. 91559-91568.
A. Fischer-Bühner, L. Anttila, M. Dev Gomony and M. Valkama (2024). Recursive Neural Network With Phase-Normalization for Modeling and Linearization of RF Power Amplifiers. IEEE Microwave and Wireless Technology Letters, vol. 34, no. 6, p. 809-812.
S.H. Javid-Hosseini, P. Ghazanfarianpoor, V. Nayyeri and P. Colantonio (2024). A Unified Neural Network-Based Approach to Nonlinear Modeling and Digital Predistortion of RF Power Amplifier. IEEE Transactions on Microwave Theory and Techniques, vol. 72, no. 9, p. 5031-5038.
T.J. Liu, S. Boumaiza and F. M. Ghannouchi (2004). Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks. IEEE Transactions on Microwave Theory and Techniques, vol. 52, no. 3, p. 1025-1033.
M. Rawat, K. Rawat and F. M. Ghannouchi (2010). Adaptive Digital Predistortion of Wireless Power Amplifiers/Transmitters Using Dynamic Real-Valued Focused Time-Delay Line Neural Networks. IEEE Transactions on Microwave Theory and Techniques, vol. 58, no. 1, p. 95-104.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Shilin Wang, Wenyuan Liu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
