Saved in:
Bibliographic Details
Main Authors: Alkadamani, Mohamad, Ghasemi, Amir, Yanikomeroglu, Halim
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.10802
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910049322926080
author Alkadamani, Mohamad
Ghasemi, Amir
Yanikomeroglu, Halim
author_facet Alkadamani, Mohamad
Ghasemi, Amir
Yanikomeroglu, Halim
contents The growing demand for wireless connectivity, combined with limited spectrum resources, calls for more efficient spectrum management. Spectrum sharing is a promising approach; however, regulators need accurate methods to characterize demand dynamics and guide allocation decisions. This paper builds and validates a spectrum demand proxy from public deployment records and uses a graph attention network in a hierarchical, multi-resolution setup (HR-GAT) to estimate spectrum demand at fine spatial scales. The model captures both neighborhood effects and cross-scale patterns, reducing spatial autocorrelation and improving generalization. Evaluated across five Canadian cities and against eight competitive baselines, HR-GAT reduces median RMSE by roughly 21% relative to the best alternative and lowers residual spatial bias. The resulting demand maps are regulator-accessible and support spectrum sharing and spectrum allocation in wireless networks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10802
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks
Alkadamani, Mohamad
Ghasemi, Amir
Yanikomeroglu, Halim
Networking and Internet Architecture
Artificial Intelligence
Machine Learning
Systems and Control
The growing demand for wireless connectivity, combined with limited spectrum resources, calls for more efficient spectrum management. Spectrum sharing is a promising approach; however, regulators need accurate methods to characterize demand dynamics and guide allocation decisions. This paper builds and validates a spectrum demand proxy from public deployment records and uses a graph attention network in a hierarchical, multi-resolution setup (HR-GAT) to estimate spectrum demand at fine spatial scales. The model captures both neighborhood effects and cross-scale patterns, reducing spatial autocorrelation and improving generalization. Evaluated across five Canadian cities and against eight competitive baselines, HR-GAT reduces median RMSE by roughly 21% relative to the best alternative and lowers residual spatial bias. The resulting demand maps are regulator-accessible and support spectrum sharing and spectrum allocation in wireless networks.
title Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks
topic Networking and Internet Architecture
Artificial Intelligence
Machine Learning
Systems and Control
url https://arxiv.org/abs/2603.10802