DRNet: Deep Learning-Based Dual-Branch Receiver for OFDM With Nonlinear Distortions
IEEE Communications Letters · 2026 · 30 · 357-361
DOI: 10.1109/lcomm.2025.3640607 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Qing Jin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 11 Literaturangaben. Gefördert von: National Natural Science Foundation of China, 111 Project.
Abstract (Originalsprache)
The nonlinear characteristics of high power amplifiers (HPAs) significantly degrade the transmission quality of orthogonal frequency division multiplexing (OFDM) system. Deep learning (DL)-based receivers have become a current research hotspot, offering lower complexity and stronger environmental adaptability than the transmitter-side through centralized digital signal processing. Existing DL receivers have mainly dealt with the frequency domain, with limited exploration of time-domain properties. In this letter, we propose a novel deep learning dual-branch distortion recovery receiver (DRNet) that operates without requiring any additional processing at the transmitter and can implicitly detect and recover distorted signals. It extracts distortion features in parallel from both time and frequency domains, and uses a feature fusion mechanism to adaptively focus on important information across different dimensions. Experimental results demonstrate that DRNet significantly outperforms both traditional receivers and existing deep learning-based methods under various HPA nonlinear models and non-terrestrial networks (NTN) channels.
Förderung
- National Natural Science Foundation of China
- 111 Project
Zitieren
APA
Jin, Q., Li, X., Guo, R., & Liu, F. (2026). DRNet: Deep Learning-Based Dual-Branch Receiver for OFDM With Nonlinear Distortions. IEEE Communications Letters, 30, 357-361. https://doi.org/10.1109/lcomm.2025.3640607
Vancouver
Jin Q, Li X, Guo R, Liu F. DRNet: Deep Learning-Based Dual-Branch Receiver for OFDM With Nonlinear Distortions. IEEE Communications Letters. 2026;30:357-361. doi:10.1109/lcomm.2025.3640607
BibTeX
@article{Jin2026,
author = {Jin, Qing and Li, Xiaohui and Guo, Ruihao and Liu, Feixiang},
title = {DRNet: Deep Learning-Based Dual-Branch Receiver for OFDM With Nonlinear Distortions},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {357--361},
doi = {10.1109/lcomm.2025.3640607}
}
EUVIMED