Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks
This work addresses the need for accurate spectrum demand estimation to support spectrum sharing and allocation decisions for regulators and wireless network operators, representing an incremental improvement over existing methods.
The paper tackled the problem of estimating spectrum demand for efficient spectrum management by building a proxy from public records and using a hierarchical graph attention network (HR-GAT) to capture spatial patterns, resulting in a 21% reduction in median RMSE compared to baselines across five Canadian cities.
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.