Date of Award
Doctor of Philosophy
Dr. Ala Al-Fuqaha
Dr. Dionysios Kountanis
Dr. Mohsen Guizani
Opportunistic service differentiation, cloud resource management, intelligent transportation systems, vehicular ad hoc networks, wireless access in vehicular environment, RSU clouds
An integral part of Intelligent Transportation Systems (ITS) are Vehicular Ad hoc Networks (VANETs), which consist of vehicles with on-board units (OBUs) and fixed road-side units (RSUs). Wireless Access in Vehicular Environment (WAVE) offers QoS via service differentiation by using application defined priorities. However, WAVE has unbounded delay and is oblivious to network load and severity of vehicles with respect to their environment. Our context severity metric innovatively enhances WAVE to be sensitive to vehicle and environment interactions. Our novel Opportunistic Service Differentiation (OSD) technique, dynamically readjusts the WAVE packet priorities to improve utilization of lower latency queues, prioritizing packets in order of context severity. This also overcomes the unbounded delay in WAVE, which is crucial for safety applications.
On the other end, our novel RSU Cloud is a unique approach to hosting non-safety services on specialized RSU micro-datacenters. Optimal provisioning of constrained resources is critical in RSU Clouds. Furthermore, inherently dynamic demands from the vehicles require replications, migrations and, or instantiations of new or existing services, on virtual machines (VMs) in the RSU Cloud. We leverage the deep programmability of Software Defined Networking (SDN) to dynamically reconfigure the RSU Cloud. However, frequent changes to service hosts and data flows not only result in degradation of services, but are also costly for service providers. In Mininet, we analyze this reconfiguration overhead, which is used to design and model optimal RSU Cloud resource management (CRM).
CRM will optimally select service hosts and data forwarding rules, such that, the reconfigurations in the network are minimized with varying demands. We begin by designing the Pareto Optimal Frontier of non-dominated solutions (POF), such that, each solution is a configuration that minimizes either the number of service instances or the RSU Cloud infrastructure delay. The network is a priori configured for some demand and, now, the optimal CRM selects a configuration from the POF that minimizes the reconfiguration costs for the new demand. Together, CRM and OSD can improve QoS for ITS applications.
Salahuddin, Mohammad Ali, "Opportunistic Service Differentiation and Cloud Resource Management in Support of Enhanced Vehicular Applications" (2014). Dissertations. 292.