analiza aiqbench
This study investigates whether generic ray-traced city models serve as superior priors for channel estimation compared to standard 3GPP stochastic models, finding that while simulations show marginal gains, real-world measurements reveal significant performance degradation when using the ray-traced approach. The research highlights a critical gap between idealized simulated environments and physical reality, demonstrating that classical statistical models often outperform geometric ray tracing in actual deployment scenarios due to simulation artifacts. Ultimately, the findings suggest that learned estimators offer limited advantage over simple classical methods for this specific task, challenging the assumption that high-fidelity digital twins automatically improve wireless link prediction.
Do Ray-Traced Cities Make a Better Channel Prior for an Unseen Site? A Pre-Registered Study in Simulation, and a Test on Measured Channels that Reverses It
arXiv:2611.05128v1 Announce Type: new Abstract: Channel estimators at a newly deployed base station usually start from 3GPP stochastic channel models, which describe no particular street. We ask whether a channel prior pooled from many ray-traced cities serves an unseen site better than the 3GPP CDL models, and whether learned estimators make the difference. With Sionna RT on 14 city scenes, LMMSE estimation from covariance priors, leave-one-city-out evaluation, and pass/fail bars written down before each main experiment, we find in simulation that the pooled prior sits about 0.6 dB from a site-trained estimator with no site measurements, about what CDL reaches after 50 measurements. Learned models added little: at most 0.65 dB in estimation, and in channel prediction a simple classical method beat CNN predictors by 1.8-12 dB from 2 ms ahead. On measured channels from the DICHASUS outdoor dataset (1.272 GHz, three 2x8 arrays on one building) the result reversed: the pooled ray-traced prior was 3.2-4.1 dB worse than CDL. The simulated channels were too clean; with users at the real distances, even a scattering level tuned from 50 site measurements left the prior about 2 dB behind CDL. A pre-registered follow-on on two more measured environments found the generic CDL prior 2.1-4.7 dB from a site-trained one: no further in a factory hall than on the street, furthest in a small lab room. Finally, a hallway model calibrated to measurements by differentiable ray tracing reproduced delay spread, but as a prior in an unmeasured part of the hallway it was 4.5 dB worse than CDL on the full array. All measured results come from one sounder.
Title:Do Ray-Traced Cities Make a Better Channel Prior for an Unseen Site? A Pre-Registered Study in Simulation, and a Test on Measured Channels that Reverses It
Abstract:Channel estimators at a newly deployed base station usually start from 3GPP stochastic channel models, which describe no particular street. We ask whether a channel prior pooled from many ray-traced cities serves an unseen site better than the 3GPP CDL models, and whether learned estimators make the difference. With Sionna RT on 14 city scenes, LMMSE estimation from covariance priors, leave-one-city-out evaluation, and pass/fail bars written down before each main experiment, we find in simulation that the pooled prior sits about 0.6 dB from a site-trained estimator with no site measurements, about what CDL reaches after 50 measurements. Learned models added little: at most 0.65 dB in estimation, and in channel prediction a simple classical method beat CNN predictors by 1.8-12 dB from 2 ms ahead. On measured channels from the DICHASUS outdoor dataset (1.272 GHz, three 2x8 arrays on one building) the result reversed: the pooled ray-traced prior was 3.2-4.1 dB worse than CDL. The simulated channels were too clean; with users at the real distances, even a scattering level tuned from 50 site measurements left the prior about 2 dB behind CDL. A pre-registered follow-on on two more measured environments found the generic CDL prior 2.1-4.7 dB from a site-trained one: no further in a factory hall than on the street, furthest in a small lab room. Finally, a hallway model calibrated to measurements by differentiable ray tracing reproduced delay spread, but as a prior in an unmeasured part of the hallway it was 4.5 dB worse than CDL on the full array. All measured results come from one sounder.
Machine Learning (cs.LG); Information Theory (cs.IT); Signal Processing (eess.SP)
arXiv:2611.05128 [cs.LG]
(or arXiv:2611.05128v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2611.05128 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 388 cuvinte
Subiecte conexe
When the AI Leaves the Tailorshop: Measuring What an LLM Advisor Leaves Behind in Complex Problem Solving
arXiv · 2 oct. 2026
Learning to Clarify Underspecified Intents Under Limited Interaction
arXiv · 7 oct. 2026
Rethinking Demonstration Unlearning in Imitation Learning for Robotics
arXiv · 24 aug. 2026
Human diversity fuels collective creativity that large language models cannot simulate or sustain
arXiv · 31 iul. 2026