An Adaptive Service Vehicle Selection Algorithm for Multihop Task Offloading in Vehicular Networks

This paper investigates the multihop task offloading problem in a vehicular network. The problem is formulated as an optimization problem with an objective to select a set of optimal service vehicles for the tasks of a task vehicle such that the maximum task service delay among all the tasks is minimized while the delay constraints of the tasks and the resource constraints of the service vehicles are guaranteed. To solve the problem, a service vehicle searching mechanism is proposed to search for candidate service vehicles for a task vehicle by exploring available multihop paths based on the connection statuses of the paths between the task vehicle and the candidate service vehicles, and the driving statuses of all vehicles in the network. Moreover, an adaptive service vehicle selection (AdSVS) algorithm is further proposed to select a set of optimal service vehicles among all the candidate service vehicles for offloading the tasks of the task vehicle. The proposed algorithm incorporates a bat algorithm and a particle swarm optimization (PSO) algorithm, which can improve the performance of task offloading. Simulation results show that the proposed Ad-SVS algorithm outperforms several benchmark algorithms in terms of the maximum task service delay.