PINN and GNN-based RF Map Construction for Wireless Communication Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Lizhou, Chen, Xiaohui, Tang, Zihan, Ma, Mengyao, Zhang, Wenyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918413731889152
author Liu, Lizhou
Chen, Xiaohui
Tang, Zihan
Ma, Mengyao
Zhang, Wenyi
author_facet Liu, Lizhou
Chen, Xiaohui
Tang, Zihan
Ma, Mengyao
Zhang, Wenyi
contents Radio frequency (RF) map is a promising technique for capturing the characteristics of multipath signal propagation, offering critical support for channel modeling, coverage analysis, and beamforming in wireless communication networks. This paper proposes a novel RF map construction method based on a combination of physics-informed neural network (PINN) and graph neural network (GNN). The PINN incorporates physical constraints derived from electromagnetic propagation laws to guide the learning process, while the GNN models spatial correlations among receiver locations. By parameterizing multipath signals into received power, delay, and angle of arrival (AoA), and integrating both physical priors and spatial dependencies, the proposed method achieves accurate prediction of multipath parameters. Experimental results demonstrate that the method enables high-precision RF map construction under sparse sampling conditions and delivers robust performance in both indoor and complex outdoor environments, outperforming baseline methods in terms of generalization and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22513
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PINN and GNN-based RF Map Construction for Wireless Communication Systems
Liu, Lizhou
Chen, Xiaohui
Tang, Zihan
Ma, Mengyao
Zhang, Wenyi
Signal Processing
Radio frequency (RF) map is a promising technique for capturing the characteristics of multipath signal propagation, offering critical support for channel modeling, coverage analysis, and beamforming in wireless communication networks. This paper proposes a novel RF map construction method based on a combination of physics-informed neural network (PINN) and graph neural network (GNN). The PINN incorporates physical constraints derived from electromagnetic propagation laws to guide the learning process, while the GNN models spatial correlations among receiver locations. By parameterizing multipath signals into received power, delay, and angle of arrival (AoA), and integrating both physical priors and spatial dependencies, the proposed method achieves accurate prediction of multipath parameters. Experimental results demonstrate that the method enables high-precision RF map construction under sparse sampling conditions and delivers robust performance in both indoor and complex outdoor environments, outperforming baseline methods in terms of generalization and accuracy.
title PINN and GNN-based RF Map Construction for Wireless Communication Systems
topic Signal Processing
url https://arxiv.org/abs/2507.22513