Parked Vehicle Edge Computing: Exploiting Opportunistic Resources for Distributed Mobile Applications

Abstract

Vehicular Edge Computing (VEC) has been studied as an important application of mobile edge computing in vehicular networks. Usually, the generalization of VEC involves large-scale deployment of dedicated servers, which will cause tremendous economic expense. We also observe that the Parked Vehicles (PVs) in addition to mobile vehicles have rich and underutilized resources for task execution in vehicular networks. Thus, we consider scheduling PVs as available edge computing nodes to execute tasks, and this leads to a new computing paradigm, called by parked vehicle edge computing (PVEC). In this paper, we investigate PVEC and explore opportunistic resources from PVs to run distributed mobile applications. PVs coordinate with VEC servers for collective task execution. First, a system architecture with primary network entities is proposed for enabling PVEC. We also elaborately design an interactive protocol to support mutual communications among them with security guarantee. Moreover, we measure the availability of opportunistic resources and formulate a resource scheduling optimization problem by using Stackelberg game approach. A subgradient-based iterative algorithm is presented to determine workload allocation among PVs and minimize the overall cost of users. Numerical results indicate that compared with existing schemes, PVEC serves more vehicles and reduces service fee for users. We also demonstrate that the Stackelberg game approach is effective and efficient.

Keywords

• Edge computing
• intelligent vehicles
• computational efficiency
• resource management