AI 中文总结
针对NR-V2X网络中RSU部署有限导致的连接不稳定问题，提出基于GNN的L2O框架实现实时多跳中继选择，以MILP最优解为监督训练GINE模型，在真实城市数据上恢复11.3%连接增益并实现100倍加速。
AI 中文摘要
可靠且低延迟的通信是NR-V2X网络所支持的智能城市服务和工业4.0应用的基本要求。然而，有限的路侧单元（RSU）部署和复杂的城市传播条件常常使网联自动驾驶车辆（CAV）无法保持稳定的连接。本文提出了一种基于图神经网络（GNN）的AI驱动的学习优化（L2O）框架，用于NR-V2X系统中的实时多跳中继选择。车载网络被建模为图，其中节点代表CAV和RSU，边编码无线链路特征。离线混合整数线性规划（MILP）公式提供最优中继决策，作为训练具有边特征的边感知图同构网络（GINE）的监督信号。在真实城市数据集上进行的大量实验表明，所提出的方法实现了接近最优的连接性能，恢复了高达11.3%的连接增益，同时与MILP相比，执行时间减少了数个数量级（高达100倍加速）。该框架实现了可扩展的实时网络控制，使其适用于智能城市和工业4.0部署。
英文摘要
Reliable and low-latency communication is a fundamental requirement for smart city services and Industry 4.0 applications enabled by NR-V2X networks. However, limited Road-Side Unit (RSU) deployment and complex urban propagation conditions often prevent Connected and Automated Vehicles (CAVs) from maintaining stable connectivity. This paper proposes an AI-driven Learning-to-Optimise (L2O) framework based on Graph Neural Networks (GNNs) for real-time multi-hop relay selection in NR-V2X systems. The vehicular network is modelled as a graph, where nodes represent CAVs and RSUs, and edges encode radio-link characteristics. An offline Mixed-Integer Linear Programming (MILP) formulation provides optimal relay decisions used as supervision for training an edge-aware Graph Isomorphism Network with Edge Features (GINE). Extensive experiments on realistic urban datasets demonstrate that the proposed approach achieves near-optimal connectivity performance, recovering up to 11.3% connectivity gain, while reducing execution time by orders of magnitude (up to 100 x speed-up) compared to MILP. The framework enables scalable and real-time network control, making it suitable for smart city and Industry 4.0 deployments.
Comments6 pages, conference
Journal ref2026 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), Bali, Indonesia, 2026, pp. 311-316
DOI：10.1109/IAICT71158.2026.11620883
