Future Connected and Automated Vehicles (CAVs) will be supervised by cloud-based systems overseeing the overall security and orchestrating traffic flows. Such systems rely on data collected from CAVs across the whole city operational area. This paper develops a Fog Computing-based infrastructure for future Intelligent Transportation Systems (ITSs) enabling an agile and reliable off-load of CAV data. Since CAVs are expected to generate large quantities of data, it is not feasible to assume data off-loading to be completed while a CAV is in the proximity of a single Road-Side Unit (RSU). CAVs are expected to be in the range of an RSU only for a limited amount of time, necessitating data reconciliation across different RSUs, if traditional approaches to data off-load were to be used. To this end, this paper proposes an agile Fog Computing infrastructure, which interconnects all the RSUs so that the data reconciliation is solved efficiently as a by-product of deploying the Random Linear Network Coding (RLNC) technique. Our numerical results confirm the feasibility of our solution and show its effectiveness when operated in a large-scale urban testbed.
@article{arxiv.1903.01377,
title = {Agile Data Offloading over Novel Fog Computing Infrastructure for CAVs},
author = {Andrea Tassi and Ioannis Mavromatis and Robert Piechocki and Andrew Nix and Christian Compton and Tracey Poole and Wolfgang Schuster},
journal= {arXiv preprint arXiv:1903.01377},
year = {2022}
}