Heterogeneous Graph Neural Network-Based Collaborative Spectrum Management for Multi-Node Frequency-Usage Network
TL;DR
The simulation results demonstrate that the proposed HGNN framework achieves steady-state utility gains of approximately 7.1% and 1.4% over the SL-GNN in 48-node and 81-node scenarios, respectively, along with corresponding Interference Suppression Ratio (ISR) improvements of 1.5 dB and 2.9 dB against the SL-GNN.
Abstract
The proliferation of UAVs operating in complex interference environments has intensified the demand for collaborative spectrum management to mitigate interference and maximize network capacity. This paper proposes a heterogeneous graph neural network (HGNN) framework for collaborative spectrum management in hierarchical UAV communication networks. The proposed architecture consists of three layers: a Terminal Transmission and Control Layer for local spectrum monitoring, a Sub-Domain Transmission and Control Layer for regional interference localization, and a Global Control Layer for network-wide spectrum optimization. Each layer incorporates multiple sensing UAVs that communicate exclusively with their own layer’s Transmission and Control UAV (T&C UAV), which aggregates and processes data from its subordinate sensing nodes and forwards the result upward through the T&C UAV chains. A hierarchical heterogeneous graph neural network with intra-layer and inter-layer message passing mechanisms was designed to capture the complex spatial–temporal dependencies in the spectrum environment under non-uniform interference conditions. The simulation results demonstrate that the proposed HGNN framework achieves steady-state utility gains of approximately 7.1% and 1.4% over the SL-GNN in 48-node and 81-node scenarios, respectively, along with corresponding Interference Suppression Ratio (ISR) improvements of 1.5 dB and 2.9 dB against the SL-GNN.