Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks

TL;DR

This paper presents a novel graph neural network-based approach for estimating spectrum demand at fine spatial resolutions, improving accuracy and bias reduction for better spectrum management.

Contribution

It introduces a hierarchical, multi-resolution graph attention network that captures neighborhood and cross-scale effects for demand estimation, validated on real city data.

Findings

Reduces median RMSE by 21% compared to baselines

Lowers residual spatial bias in demand estimates

Provides regulator-accessible demand maps for spectrum sharing

Abstract

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.