Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning

The recent publication titled 'Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning' introduces a novel approach to dual-technology scheduling in IoT networks that integrate Optical Wireless Communication (OWC) and Radio Frequency (RF). The authors tackle the complex problem using a Mixed-Integer Nonlinear Programming (MINLP) model aimed at maximizing throughput while minimizing delays, constrained by energy and link availability. Given the challenges of solving NP-hard problems at scale, they propose the Dual-Graph Embedding with Transformer (DGET) framework, which combines transductive and inductive Graph Neural Networks (GNNs) for effective scheduling. Simulation results indicate that hybrid RF-OWC networks outperform traditional methods, highlighting the potential of this framework to enhance IoT network performance. This work is particularly relevant as the demand for efficient resource allocation in IoT systems continues to grow, making adva…