Why Channel-Centric Models are not Enough to Predict End-to-End Performance in Private 5G: A Measurement Campaign and Case Study

TL;DR

This study shows that channel-centric models are insufficient for predicting end-to-end performance in private 5G environments, highlighting the need for data-driven approaches or extensive calibration for accurate throughput estimation.

Contribution

The paper provides a comprehensive measurement campaign and case study demonstrating the limitations of channel-centric models and the effectiveness of data-driven Gaussian process regression in predicting 5G throughput.

Findings

Ray-tracing models over-predict throughput due to MIMO layer assumptions.

Gaussian process models reduce prediction error by approximately two-thirds.

Channel conditions alone do not reliably indicate end-to-end throughput.

Abstract

Communication-aware robot planning requires accurate predictions of wireless network performance. Current approaches rely on channel-level metrics such as received signal strength and signal-to-noise ratio, assuming these translate reliably into end-to-end throughput. We challenge this assumption through a measurement campaign in a private 5G industrial environment. We evaluate throughput predictions from a commercial ray-tracing simulator as well as data-driven Gaussian process regression models against measurements collected using a mobile robot. The study uses off-the-shelf user equipment in an underground, radio-shielded facility with detailed 3D modeling, representing a best-case scenario for prediction accuracy. The ray-tracing simulator captures the spatial structure of indoor propagation and predicts channel-level metrics with reasonable fidelity. However, it systematically over-predicts throughput, even in line-of-sight regions. The dominant error source is shown to be over-estimation of sustainable MIMO spatial layers: the simulator assumes near-uniform four-layer transmission while measurements reveal substantial adaptation between one and three layers. This mismatch inflates predicted throughput even when channel metrics appear accurate. In contrast, a Gaussian process model with a rational quadratic kernel achieves approximately two-thirds reduction in prediction error with near-zero bias by learning end-to-end throughput directly from measurements. These findings demonstrate that favorable channel conditions do not guarantee high throughput; communication-aware planners relying solely on channel-centric predictions risk overly optimistic trajectories that violate reliability requirements. Accurate throughput prediction for 5G systems requires either extensive calibration of link-layer models or data-driven approaches that capture real system behavior.