| Summary: | In recent years, Vehicular Edge Computing (VEC) has emerged as one solution to tackle the challenge of reliable and fast service provisioning of Vehicular Applications in Vehicular Networks and to accelerate the advent of Smart Vehicles. This paradigm consists of leveraging the ever-increasing computational and storage capabilities provided by the devices in the Network Edge, which are near to the end-users, in complement with the services provided by Cloud Computing. The exponential growth of information to process, the latency-sensitive nature of the vehicular applications and the high mobility of the vehicles, constitute considerable real-world challenges that need to be addressed for VEC to perform adequately. Thus, a need arises in devising better-performing methods to manage the backhaul Edge and network infrastructure to provide continuous service to vehicular clients. In the proposed thesis, we will study the State-of-the-Art on heuristics and other strategies to manage an infrastructure of Edge nodes where components of the computation of vehicular applications will be hosted, as a function of the Vehicle-to-Infrastructure communication Quality of Service and capacity and availability of the Edge nodes. As a result of this thesis, a new heuristic, or improvements over existing ones, is expected to be produced. We will conduct the development and test of these algorithms over a system world that uses the Manhattan grid topology.
|
|---|