Routing Algorithms for Heterogeneous Vehicular Networks

Abstract

AbstractWith the ever-increasing demand for ubiquitous communications from vehicles, there is an increasing request for Internet of Vehicles (IoV). IoV has been envisioned as an enabling technology for the next-generation mobile networks by using vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P), and vehicle-to-sensor (V2S) interactions and connections. It is anticipated that IoV will pave the way for supporting real-time applications for road safety, smart and green transportation, location-specific services, and in-vehicle Internet access. However, establishing and maintaining end-to-end connections in an IoV network is challenging due to the high vehicle mobility, dynamic inter-vehicle spacing, and variable vehicle density. This chapter focuses on routing algorithms review for the IoV. First, the background and knowledge of routing algorithms are introduced. Then, a centralized routing scheme with mobility prediction (CRS-MP) for IoV assisted by a software-defined network (SDN) controller powered with artificial intelligence is introduced. Specifically, through advanced artificial neural network (ANN) technique, the SDN controller is able to perform mobility prediction to deal with frequent network topology changes, so the probabilities of successful transmissions and average delay of each vehicle’s request can be estimated by the roadside units (RSUs) or the base station (BS). Mobility prediction is performed based on a stochastic urban traffic model in which the vehicle arrivals follow a non-homogeneous Poisson process (NHPP). The SDN controller collects network information from RSUs and BS, and they are considered as the switches. Since the SDN controller can obtain the global network information, it decides optimal routing paths for switches (i.e., BS and RSU). However, if the source vehicle and destination vehicle are located in the coverage area of the same switch, to minimize the overall service delay, the routing decision will be made by the RSUs or the BS independently, which schedules the requests of vehicles by either V2V or V2I communication, from the source vehicle to the destination vehicle.KeywordsInternet of VehiclesRouting algorithmMobility predictionNon-homogeneous Poisson processMachine learning