Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.10264 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908768595345408 |
|---|---|
| author | Zheng, Jingze Shi, Zhiguo He, Shibo Gu, Chaojie |
| author_facet | Zheng, Jingze Shi, Zhiguo He, Shibo Gu, Chaojie |
| contents | Carrier Frequency Offset (CFO) estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems faces significant performance degradation across heterogeneous software-defined radio (SDR) platforms due to uncalibrated hardware impairments. Existing deep neural network (DNN)-based approaches lack device-level adaptation, limiting their practical deployment. This paper proposes a Sim2Real transfer learning framework for per-device CFO calibration, combining simulation-driven pretraining with lightweight receiver adaptation. A backbone DNN is pre-trained on synthetic OFDM signals incorporating parametric hardware distortions (e.g., phase noise, IQ imbalance), enabling generalized feature learning without costly cross-device data collection. Subsequently, only the regression layers are fine-tuned using $1,000$ real frames per target device, preserving hardware-agnostic knowledge while adapting to device-specific impairments. Experiments across three SDR families (USRP B210, USRP N210, HackRF One) achieve $30\times$ BER reduction compared to conventional CP-based methods under indoor multipath conditions. The framework bridges the simulation-to-reality gap for robust CFO estimation, enabling cost-effective deployment in heterogeneous wireless systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10264 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sim2Real Deep Transfer for Per-Device CFO Calibration Zheng, Jingze Shi, Zhiguo He, Shibo Gu, Chaojie Signal Processing Machine Learning Carrier Frequency Offset (CFO) estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems faces significant performance degradation across heterogeneous software-defined radio (SDR) platforms due to uncalibrated hardware impairments. Existing deep neural network (DNN)-based approaches lack device-level adaptation, limiting their practical deployment. This paper proposes a Sim2Real transfer learning framework for per-device CFO calibration, combining simulation-driven pretraining with lightweight receiver adaptation. A backbone DNN is pre-trained on synthetic OFDM signals incorporating parametric hardware distortions (e.g., phase noise, IQ imbalance), enabling generalized feature learning without costly cross-device data collection. Subsequently, only the regression layers are fine-tuned using $1,000$ real frames per target device, preserving hardware-agnostic knowledge while adapting to device-specific impairments. Experiments across three SDR families (USRP B210, USRP N210, HackRF One) achieve $30\times$ BER reduction compared to conventional CP-based methods under indoor multipath conditions. The framework bridges the simulation-to-reality gap for robust CFO estimation, enabling cost-effective deployment in heterogeneous wireless systems. |
| title | Sim2Real Deep Transfer for Per-Device CFO Calibration |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2601.10264 |