EUVIMEDEUVIMED entdecken
Crossref

Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations

Qianqian Zhang, Chengye Jiang, Renlong Han, Guichen Yang, Junsen Wang, Hao Chang, Falin Liu

IEEE Transactions on Microwave Theory and Techniques · 2025-01 · 73 (1) · 436-447

DOI: 10.1109/tmtt.2024.3418014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Microwave Theory and Techniques, 2025-01. Verfasst von Qianqian Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To meet the challenge of digital predistortion (DPD) under dynamic scenarios, a structural adaptation method of neural network (NN) based on the gate mechanism is proposed. This method integrates highway network with a noise gate, achieving discrete gating network gradient backpropagation and smooth variations in the backbone network structure. Applying this method to gated dynamic NN (GDNN), the adaptive inference pathway-gated NN (AIPGNN) model is proposed. The AIPGNN is capable of adaptively activating specific finite impulse response (FIR) filter branches based on the current configuration information. In a sense, the input signal is processed only through the activated FIR filter branches, while directly passing through the inactivated FIR filter branches. This adaptive activation method allows for the training of a specialized set of FIR branches customized to the nonlinear (NL) characteristics of a particular class of configurations, while FIR branches in GDNN are required to accommodate all configurations, which results in challenging trade-offs for the FIR layer during training. Furthermore, the AIPGNN model also supports the activation of a varying number of FIR filter branches under different transmission configurations. The adaptively changed network structure enables the proposed model to adequately correct the NL behavior of the power amplifier (PA) in more complex transmission configurations, without resource wastage in simpler transmission configurations, which meets the needs of time-varying configuration scenarios. The experimental results indicate that the AIPGNN exhibits superior dynamic linearization performance and good generalization capability under varying transmission configurations.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Q., Jiang, C., Han, R., Yang, G., Wang, J., Chang, H., & Liu, F. (2025). Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations. IEEE Transactions on Microwave Theory and Techniques, 73(1), 436-447. https://doi.org/10.1109/tmtt.2024.3418014

Vancouver

Zhang Q, Jiang C, Han R, Yang G, Wang J, Chang H, et al. Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations. IEEE Transactions on Microwave Theory and Techniques. 2025;73(1):436-447. doi:10.1109/tmtt.2024.3418014

BibTeX
@article{Zhang2025,
  author = {Zhang, Qianqian and Jiang, Chengye and Han, Renlong and Yang, Guichen and Wang, Junsen and Chang, Hao and Liu, Falin},
  title = {Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations},
  journal = {IEEE Transactions on Microwave Theory and Techniques},
  year = {2025},
  volume = {73},
  number = {1},
  pages = {436--447},
  doi = {10.1109/tmtt.2024.3418014}
}
Kostenlos starten →