LAUSR

Vehicular edge computing has emerged as a promising technology to accommodate the tremendous demand for data storage and computational resources in vehicular networks. By processing the massive workload tasks in the proximity of vehicles, the quality of service can be guaranteed. However, how to determine the task offloading strategy under various constraints of resource and delay is still an open issue. In this paper, we study the task offloading problem from a matching perspective and aim to optimize the total network delay. The task offloading delay model is derived based on three different velocity models, i.e., a constant velocity model, vehicle-following model, and traveling-time statistical model. Next, we propose a pricing-based one-to-one matching algorithm and pricing-based one-to-many matching algorithms for the task offloading. The proposed algorithm is validated based on three different simulation scenarios, i.e., straight road, the urban road with the traffic light, and crooked road, which are extracted from the realistic road topologies in Beijing and Guangdong, China. The simulation results confirm that significant delay decreasing can be achieved by the proposed algorithm.