Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features

2026-07-15

AI Summary

This study addresses the challenge of unreliable sidelink communications in dense urban NR-V2X networks, where rapid channel variations and blockages render direct links unstable, and optimal multi-hop relay selection constitutes an NP-hard problem. The authors model V2X network snapshots as directed graphs with node and edge features and propose the first Graph Isomorphism Network incorporating edge features (GINE). Trained on optimal solutions generated offline via Mixed-Integer Linear Programming (MILP), GINE enables low-latency relay activation through a single forward inference pass. Furthermore, they introduce a GINE-Pruned MILP (GP-MILP) hybrid solver that drastically reduces the search space while preserving solution optimality. Experimental results demonstrate that GINE achieves a link-level decision accuracy of 0.9589 and an F1 score of 0.9544; end-to-end connectivity improves by up to 12% over single-hop MILP; pure GINE inference incurs less than 5 ms latency, and GP-MILP solves over 98% of scenarios within 30 ms with solution quality equivalent to MILP.

Abstract

Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links. Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size. This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection. Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity. An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency. To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space. Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs). Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms. Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.

Problem

• low-latency
• relay selection
• NR-V2X
• C-V2X
• NP-hard optimization

Innovation

• Graph Isomorphism Network with Edge Features
• Learning-to-Optimise
• Low-Latency Relay Selection
• Hybrid GINE-Pruned MILP
• NR-V2X