Facilitating the revolution for smarter cities, vehicles are getting smarter and equipped with more resources to go beyond transportation functionality. On-Board Units (OBU) are efficient computers inside vehicles that serve safety and non-safety based applications. However, much of these resources are underutilised. On the other hand, more users are relying now on cloud computing which is becoming costly and energy consuming. In this paper, we develop a Mixed Integer linear Programming (MILP) model that optimizes the allocation of processing demands in an architecture that encompasses the vehicles, edge and cloud computing with the objective of minimizing power consumption. The results show power savings of 70%-90% compared to conventional clouds for small demands. For medium and large demand sizes, the results show 20%-30% power saving as the cloud was used partially due to capacity limitations on the vehicular and edge nodes.
INTROUCTIONEnd users are growing more dependent on cloud services and data centers [1]. As the demand on cloud services grows higher, the data centers, as expected, tend to grow even bigger and more expensive in term of both monetary cost and energy consumptions. The energy consumption of clouds and data centers is contributing much to the total cost and power consumption in the Information and Communication Technology (ICT) field. That is why a lot of effort is being put forward now to explore alternatives that are more energy efficient and still as powerful [2][3][4][5][6][7][8][9][10][11]. One approach that is being actively evaluated is distributed service providers or the installation of mini data centers close to end users' level. In [12] data processing is done at different layers of the network and not only in the core cloud through optimized placement of Virtual Machines (VM) in IoT devices. Comparison between centralized data centers and nano data centers, to show the validity of the small data centers and its impacting factors, was carried out in [13]. The work in [14] analysed the energy consumption and latency of computation offloading in mobile clouds.Modern vehicles are increasingly being viewed as smart machines with plenty of computing resources. Research in the area of vehicular networks is very promising and it varies from Internet of Vehicles (IoV) [15] to Vehicular Clouds to VaaR (vehicle as a Resource) [16]. Our work presents an end-to-end architecture that uses vehicular and edge computing as the first level of processing resources. It compares this architecture with conventional clouds from an energy consumption point of view. For the remainder or the paper, Section 2 presents the proposed architecture. Section 3 discusses the optimization model and its results, and in Section 4 the paper is concluded.