Site-Specific Finetuning of Neural Receivers with Real-World 5G NR Measurements

TL;DR

This paper demonstrates that site-specific finetuning of neural wireless receivers using real-world 5G measurements significantly improves error rates across various environments and hardware, confirming prior synthetic data findings.

Contribution

It provides the first real-world benchmark validation of site-specific neural receiver finetuning for 5G, showing consistent performance gains across diverse scenarios.

Findings

Substantial error-rate improvements from finetuning in real-world settings

Performance gains generalize across different hardware and environments

Validates earlier synthetic data results with real-world measurements

Abstract

Finetuning wireless receivers to a specific deployment scenario can yield significant error-rate performance improvements without increasing processing complexity. However, site-specific finetuning has so far only been demonstrated on synthetic channel data and lacks real-world benchmarks. In this work, we empirically study site-specific finetuning of neural receivers using real-world 5G NR physical uplink shared channel (PUSCH) data collected with an over-the-air testbed at ETH Zurich across three scenarios: (i) a small laboratory, (ii) a large office floor, and (iii) a high-mobility outdoor environment. Our results confirm substantial error-rate performance improvements from site-specific finetuning, consistent with earlier findings based on synthetic channel data. Moreover, we demonstrate that these improvements generalize across different user-equipment hardware and deployment scenarios.