AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks

2026-07-15

AI Summary

In dense urban environments, NR-V2X networks struggle to maintain stable single-hop connectivity for connected and automated vehicles (CAVs) due to sparse roadside unit (RSU) deployment, non-line-of-sight propagation, and highly dynamic vehicular topologies. To address this challenge, this work proposes the first learning-to-optimize (L2O) framework integrated with graph neural networks, specifically leveraging GINE for multi-hop relay selection. The approach constructs propagation-aware, attribute-enriched graphs through joint SUMO–GEMV2 simulation and trains the model using offline optimal solutions derived from mixed-integer linear programming (MILP). Experimental results demonstrate that the proposed method achieves near-optimal connectivity performance in large-scale urban scenarios while reducing inference latency to nearly constant time, thereby significantly enhancing system scalability and real-time responsiveness.

Abstract

Reliable and low-latency NR-V2X communications are essential for smart mobility in dense urban environments. However, limited Road-Side Unit (RSU) density, frequent non-line-of-sight conditions, and highly dynamic vehicular topologies often prevent many Connected and Automated Vehicles (CAVs) from maintaining stable single-hop connectivity. Although multi-hop relay-assisted communication can extend infrastructure coverage, selecting relay links in real time under practical flow, capacity, and connectivity constraints remains challenging. Mixed-Integer Linear Programming (MILP) yields optimal multi-hop relay decisions, but its computational complexity scales sharply with network density, limiting real-time applicability. To address this, we propose a Learning-to-Optimise (L2O) framework based on Graph Neural Networks (GNNs) for real-time NR-V2X relay selection. Vehicular communication states are modeled as attributed graphs, where CAVs and RSUs are nodes and candidate radio links are enriched with propagation-aware features. An offline MILP oracle provides optimal supervision, while an edge-aware Graph Isomorphism Network (GINE) approximates oracle decisions with near-constant inference latency. Experiments on large-scale urban datasets generated by an integrated SUMO--GEMV2 simulation pipeline show that the proposed approach achieves connectivity comparable to that of the MILP oracle while reducing execution time by orders of magnitude. The framework enables cost-effective enhancement of urban V2X connectivity by leveraging existing vehicular assets and supporting scalable, real-time NR-V2X operation in smart city environments.

Problem

• NR-V2X
• multi-hop relay selection
• real-time communication
• urban vehicular networks
• connectivity constraints

Innovation

• Learning-to-Optimize
• Graph Neural Networks
• NR-V2X
• Multi-hop Relay Selection
• Real-time Optimization