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

2026-03-11

AI Summary

This study addresses the critical challenge of accurately estimating fine-grained spectrum demand under constrained spectral resources, which is essential for efficient spectrum sharing. The authors propose a Hierarchical Multi-Resolution Graph Attention Network (HR-GAT) that leverages publicly available deployment data to construct proxy indicators of spectrum demand. By integrating multi-scale spatial structural information, HR-GAT effectively models both local neighborhood effects and cross-scale dependencies, substantially reducing spatial autocorrelation and residual bias. Experimental evaluations across five Canadian cities demonstrate that the proposed method achieves approximately a 21% reduction in median RMSE compared to the best-performing baseline. The resulting high-fidelity spectrum demand maps offer actionable insights for regulatory bodies in making informed spectrum allocation decisions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: The sharing economy

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.

Problem

• spectrum demand estimation
• spectrum management
• spectrum sharing
• spatial scale
• wireless networks

Innovation

• Graph Neural Networks
• Spectrum Demand Estimation
• Hierarchical Multi-resolution Modeling
• Spatial Autocorrelation Reduction
• Spectrum Sharing