Research Output
Reliable and Scalable Routing Under Hybrid SDVN Architecture: A Graph Learning Based Method
  Greedy routing efficiently achieves routing solutions for vehicular networks due to its simplicity and reliability. However, the existing greedy routing schemes have mainly considered simple routing metrics only, e.g., distance based on the local view of an individual vehicle. This consideration is insufficient for analysing dynamic and complicated vehicular communication scenarios. This shortcoming inevitably degrades the overall routing performance. Software-Defined Vehicular Network (SDVN) and Graph Convolutional Network (GCN) could break these limitations. Thus, this paper presents a novel GCN-based greedy routing algorithm (NGGRA) in the hybrid SDVN. The SDVN control plane trains the GCN decision model based on the globally collected data. The vehicle with transmission requirements can adopt this model for inferring and making the routing decision. The new proposed nodeimportance-based graph convolutional network (NiGCN) model analyses multiple metrics in the dynamic vehicular network scenario. Meanwhile, SDVN architecture offers a global view for model training. Extensive simulation results demonstrate that NiGCN outperforms most popular GCN models in training efficiency and accuracy. In addition, NGGRA can improve the packet delivery ratio and latency substantially compared with its counterparts.

  • Type:


  • Date:

    09 August 2023

  • Publication Status:


  • Publisher

    Institute of Electrical and Electronics Engineers (IEEE)

  • DOI:


  • ISSN:


  • Funders:

    National Natural Science Foundation of China; New Funder


Li, Z., Zhao, L., Min, G., Al-Dubai, A. Y., Hawbani, A., Zomaya, A. Y., & Luo, C. (2023). Reliable and Scalable Routing Under Hybrid SDVN Architecture: A Graph Learning Based Method. IEEE Transactions on Intelligent Transportation Systems, 24(12), 14022 - 14036.



Software-defined vehicular networks, vehicular ad-hoc networks, routing, deep learning, graph convolutional networks

Monthly Views:

Available Documents