{"ID":6537552,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11429","arxiv_id":"2607.11429","title":"Physics-Aware Conditional SetGAN for Spatially Consistent Multi-User TR 38.901 Channel Generation","abstract":"TR 38.901-based channel models such as Sionna are reliable, but generating many multi-user channel realizations remains expensive. This paper asks a practical question: can a trained generative model produce multi-user TR 38.901 channels faster than Sionna without losing the spatial correlations imposed by user geometry? To answer this question, we propose a physics-aware, geometry-conditioned SetGAN trained on Sionna reference data. The method separates large-scale received power from normalized small-scale fading, compresses the latter with principal component analysis, and learns the conditional channel distribution in a latent space while preserving geometry-dependent correlations. On the UMa/NLoS benchmark, the model keeps the received-power distributions close to the reference, with about 0.41 dB Wasserstein distance, and reproduces spatial-consistency profiles with mean deviations below 0.03 on median curves versus distance. In addition, it reduces elapsed generation time by a factor of 3.45 and CPU-total cost by a factor of 6.15 relative to Sionna under matched user positions in the fixed-position CPU-vs-CPU benchmark. These results show that a trained generative model can substantially accelerate TR 38.901 channel generation without breaking the spatial consistency needed to evaluate multi-user systems.","short_abstract":"TR 38.901-based channel models such as Sionna are reliable, but generating many multi-user channel realizations remains expensive. This paper asks a practical question: can a trained generative model produce multi-user TR 38.901 channels faster than Sionna without losing the spatial correlations imposed by user geometr...","url_abs":"https://arxiv.org/abs/2607.11429","url_pdf":"https://arxiv.org/pdf/2607.11429v1","authors":"[\"Mauro Gonzalo Tarazona-Levano\",\"David Lopez-Perez\",\"Nicola Piovesan\",\"David Gomez-Barquero\"]","published":"2026-07-13T11:36:08Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}