Scheduling Algorithm for Vehicle to Road-Side Data Distribution

We investigate the problem of scheduling of file distribution from Road-Side Units (RSUs) to vehicles in an urban environment. We suppose one RSU exist in each cross-road and all RSUs are connected to each other through a high speed backbone. Since the number of vehicles as well as the number and size of files are potentially large, scalable scheduling is a challenge. We first chop each file into several segments. A vehicle may not be able to finish downloading all segments from a RSU, thus, our proposed algorithm allows it to continue its download from the next RSUs. We propose a scheduling algorithm in which each RSU implements two separate queues for: 1) download requests from the scratch and 2) resumed downloads. The data segment for distribution is chosen from aforementioned queues based on some scheduling policies. Simulation result shows that the proposed approach offer desirable performance and scalability.