Optimized Distributed Processing in a Vehicular Cloud Architecture

Abstract

The introduction of cloud data centres has opened new possibilities for the storage and processing of data, augmenting the limited capabilities of peripheral devices. Large data centres tend to be located away from the end users, which increases latency and power consumption in the interconnecting networks. These limitations led to the introduction of edge processing where small-distributed data centres or fog units are located at the edge of the network close to the end user. Vehicles can have substantial processing capabilities, often un-used, in their on-board-units (OBUs). These can be used to augment the network edge processing capabilities. In this paper, we extend our previous work and develop a mixed integer linear programming (MILP) formulation that optimizes the allocation of networking and processing resources to minimize power consumption. Our edge processing architecture includes vehicular processing nodes, edge processing and cloud infrastructure. Furthermore, in this paper our optimization formulation includes delay. Compared to power minimization, our new formulation reduces delay significantly, while resulting in a very limited increase in power consumption.