dorsal/arxiv
View SchemaSim2Real Deep Transfer for Per-Device CFO Calibration
| Authors | Jingze Zheng, Zhiguo Shi, Shibo He, Chaojie Gu |
|---|---|
| Categories | |
| ArXiv ID | 2601.10264vv1 |
| URL | https://arxiv.org/abs/2601.10264 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
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.
{
"annotation_id": "e3975414-1e64-4a9a-932f-26368ccedf8c",
"date_created": "2026-02-17T05:53:24.278000Z",
"date_modified": "2026-02-17T05:53:24.278000Z",
"file_hash": "d24ef7c2f3aae938ef26589191997f139a1eebaf1512971c8efb208817d7cd9d",
"private": false,
"record": {
"abstract": "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.",
"arxiv_id": "2601.10264",
"authors": [
"Jingze Zheng",
"Zhiguo Shi",
"Shibo He",
"Chaojie Gu"
],
"categories": [
"eess.SP",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Sim2Real Deep Transfer for Per-Device CFO Calibration",
"url": "https://arxiv.org/abs/2601.10264",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f066ba5e-6db0-422e-9452-a9f607b98d87",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}