AI framework optimizes urban vehicle communication networks

Researchers have developed an AI-driven framework using Graph Neural Networks (GNNs) to optimize real-time multi-hop relay selection in smart urban NR-V2X networks. This approach models the vehicular network as a graph, using optimal relay decisions from Mixed-Integer Linear Programming (MILP) for training. Experiments show the GNN-based method achieves near-optimal connectivity, improving it by up to 11.3% while significantly reducing execution time compared to MILP. AI

影响 This research could enable more reliable and efficient communication for connected vehicles in urban environments, supporting smart city initiatives.

排序理由 The cluster contains a submitted academic paper detailing a novel AI-driven method for network optimization. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Connected and Automated Vehicles Symposium
• Federica Mangiatordi
• Graph Isomorphism Network with Edge Features
• graph neural networks
• Learning to optimise wind farms with graph transformers
• Mixed Integer Linear Programming
• NR-V2X
• Rivers State University of Science and Technology

• 论文
• 基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →