Physics-Guided Diffusion Models for Multi-Scale Prediction of Reference Signal Received Power in Wireless Networks
TL;DR
A physics-guided two-stage training scheme with a noise prior guidance mechanism, enabling effective fusion of multi-scale physical knowledge with the diffusion models, resulting in a diffusion-model-based RSRP prediction model, Channel-Diff.
Abstract
The Reference Signal Received Power (RSRP) is a crucial factor that determines communication performance in mobile networks. Accurately predicting the RSRP can help network operators perceive user experiences and maximize throughput by optimizing wireless resources. However, existing research into RSRP prediction has limitations in accuracy and verisimilitude. Theoretical derivations and existing data-driven methods consider only easily quantifiable Large-Scale (LS) information and struggle to effectively capture the intertwined LS and Small-Scale (SS) signal attenuation characteristics of the wireless channel. Moreover, the lack of guidance from propagation physics leads to weak accuracy, interpretability, and transferability. In this paper, we propose a diffusion-model-based RSRP prediction model, Channel-Diff. It takes network parameters and multi-attribute urban maps as conditioning inputs, from which large-scale propagation modelling and occlusion–shadow modelling provide LS physical knowledge, while multipath propagation modelling and a microenvironment feature extraction network characterise the conditional statistics of SS fading. We design a physics-guided two-stage training scheme with a noise prior guidance mechanism, enabling effective fusion of multi-scale physical knowledge with the diffusion models. Evaluations demonstrate that Channel-Diff exhibits excellent performance on RSRP prediction, achieving at least 25.15%–37.19% improvement in accuracy relative to baseline methods. Additionally, the model also demonstrates outstanding performance in terms of transferability and training efficiency.
