Efficient Sim2Real Deep Learning for Device-Specific OFDM Frequency Offset Calibration
IEEE Transactions on Wireless Communications · 2026 · 25 · 19355-19366
DOI: 10.1109/twc.2026.3707555 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Chaojie Gu und 5 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: National Science Fund of China, Key Research and Development Program of Zhejiang Province.
Abstract (Originalsprache)
Frequency offset estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems suffers from performance degradation across heterogeneous software-defined radio (SDR) devices due to uncalibrated hardware impairments, especially when a low-cost SDR device is used as a receiver. Existing deep neural network (DNN)-based methods lack device-level adaptability, limiting their practical use in dynamic environments. This paper introduces a Sim2Real transfer learning framework for per-device frequency offset calibration, integrating simulation-based pretraining with lightweight receiver-side adaptation. A backbone DNN is first pretrained on synthetic OFDM signals emulating parametric hardware distortions such as phase noise and IQ imbalance, enabling generalized feature extraction without the need for extensive cross-device real data collection. Subsequently, only the regression layers are fine-tuned using as few as $1,000$ real OFDM frames per target device, thus preserving hardware-independent knowledge while efficiently adapting to device-specific impairments. Experimental validation across three SDR platforms (USRP B210, USRP N210, HackRF One) demonstrates a 48% reduction in bit error rate compared to conventional cyclic prefix-based methods under indoor multipath propagation. The proposed framework effectively bridges the simulation-to-reality gap for robust frequency estimation, facilitating scalable and cost-effective deployment in heterogeneous communication systems.
Förderung
- National Science Fund of China
- Key Research and Development Program of Zhejiang Province
Zitieren
APA
Gu, C., Zheng, J., Shi, H., Yang, Y., He, S., & Shi, Z. (2026). Efficient Sim2Real Deep Learning for Device-Specific OFDM Frequency Offset Calibration. IEEE Transactions on Wireless Communications, 25, 19355-19366. https://doi.org/10.1109/twc.2026.3707555
Vancouver
Gu C, Zheng J, Shi H, Yang Y, He S, Shi Z. Efficient Sim2Real Deep Learning for Device-Specific OFDM Frequency Offset Calibration. IEEE Transactions on Wireless Communications. 2026;25:19355-19366. doi:10.1109/twc.2026.3707555
BibTeX
@article{Gu2026,
author = {Gu, Chaojie and Zheng, Jingze and Shi, Haoran and Yang, Yichuan and He, Shibo and Shi, Zhiguo},
title = {Efficient Sim2Real Deep Learning for Device-Specific OFDM Frequency Offset Calibration},
journal = {IEEE Transactions on Wireless Communications},
year = {2026},
volume = {25},
pages = {19355--19366},
doi = {10.1109/twc.2026.3707555}
}
EUVIMED