A Novel Prediction-Based Temporal Graph Routing Algorithm for Software-Defined Vehicular Networks

Temporal information is critical for routing computation in the vehicular network. It plays a vital role Till now, most existing schemes networks consider as sequence of static graphs. We need to find an appropriate method process temporal into computation. Thus, this paper, we propose algorithm based on Hidden Markov Model (HMM) and graph, namely, Prediction-Based Graph Routing Algorithm (PT-GROUT). This new considers network which each data transmission edge has its specific information. To better capture information, select Software-Defined Vehicular Network (SDVN) our architecture, preferred architecture processing graph regarding since all vehicle statuses can be easily managed. compute future path accurately efficiently, predicted by applying HMM, model current with dynamic programming greedy strategies. With reasonable setting PT-GROUT evaluate discover evolution internal structure The optimal achieved more efficiently. simulation results demonstrate that substantially improve efficiency reduce packet loss delivery delay compared counterparts.