Parked vehicles crowdsourcing for task offloading in vehicular edge computing

With computation offloading widely used in the computation-intensive vehicular applications, vehicular edge computing (VEC) faces the resource shortage of VEC servers. In this paper, the idle resources in the parked vehicles are aggregated to process the offloaded computing tasks, and the incentive schemes are proposed to encourage the parked vehicles to make the contribution to VEC. First, we propose a system architecture for task offloading, in which the edge crowdsourcing platform (ECP) is designed to manage and schedule the resources of parked vehicles for VEC, and a requesting vehicle can offload the computing tasks to the VEC server and the ECP simultaneously. Then, based on the Stackelberg game, we formulate the interactions between the participants of VEC as a task allocation optimization problem and establish a price model in which each participant can obtain their maximum utilities. Finally, we theoretically prove the existence and uniqueness of the Stackelberg equilibrium in this game, and a gradient iterative algorithm is proposed to determine the task allocation between the VEC server and the ECP, meanwhile achieving their best strategies. The simulation results demonstrate that the performance of the proposed scheme is better than that of traditional methods.