Optimal Computation Resource Allocation in Vehicular Edge Computing

Vehicular edge computing is proposed as a new promising paradigm that provides cloud computation capabilities in close proximity to vehicles, which can augment the capabilities of vehicles. In this paper, we study the problem of computation resource allocation of edge servers for a vehicular edge computing system. We consider the constraint of limited computation resource of edge servers and vehicles can decide that vehicular applications are locally executed or off loaded to edge servers for execution to minimize the completion time of applications. We model the problem as a Stackelberg game and then prove the existence of Nash equilibrium of the game. Furthermore, we propose an algorithm to compute the Nash equilibrium effectively. Numerical simulation results demonstrate that our proposed algorithm can greatly reduce the average completion time for all applications and outperform the benchmark approaches.