学术文献库

Vehicular edge computing is a new distributed processing architecture that exploits the revolution in the processing capabilities of vehicles to provide energy efficient services and low delay for Internet of Things (IoT)-based systems. Edge computing relies on a set of distributed processing nodes (i.e. vehicles) that are located close to the end user. In this paper, we consider a vehicular edge cloud (VEC) consisting of a set of vehicle clusters that form a temporal vehicular cloud by combining their computational resources in the cluster. We tackle the problem of processing allocation in the proposed vehicular edge architecture by developing a Mixed Integer Linear Programming (MILP) optimization model that jointly minimizes power consumption, propagation delay, and queuing delay. The results show that the closer the processing node (PN) is to the access point (AP), the lower the power consumption and delay, as the distance and number of hops affect the propagation delay and queuing delay. However, the queuing delay at the AP becomes a limiting factor when it operates at a low service rate compared to the traffic arrival rate. Thus, processing tasks at the vehicular nodes (VN) was avoided whenever the objective function included queueing delay and the AP operated at a low service rate. Increase in the AP service rate results in a lower queuing delay and better VN utilization.