| As with all Future Internet (FI) technologies, resource allocation remains an issue that needs to be addressed. Furthermore, as an emerging technology, cloud computing has also encountered this same issue. OpenStack is a cloud computing operating system which aims to provide an open source cloud computing platform for both public and private clouds. In terms of infrastructure as a service (IaaS) platform, the OpenStack cloud platform faces a resource allocation limitation problem.Over the last few years, network virtualization has been an extremely important technology. It is widely used for running multiple architectures simultaneously over a shared infrastructure. However, making a more efficient use of resources would require effective techniques associated with virtual network embedding. These categories of techniques are generally referred to as Virtual Network Embedding (VNE) algorithms or strategies.This thesis focuses on the research and implementation of a virtual network em-bedding strategy within the OpenStack cloud platform. The project has been divided into two sections. The first section contains an intensive study and research into the OpenStack cloud platform and the problems associated with virtual network embedding. These problems involve code reading, analyzing, debugging, and bandwidth testing. The second section involves a customization of OpenStack Dashboard (horizon) to gen-erate virtual network requests and then processing these requests. It also uses Open-Stack Compute (Nova) to provide bandwidth limitations for the virtual network re-quests, as well as a modification of the data structure used between the OpenStack Hori-zon and Nova Modules. It implements a proposed virtual network embedded problem algorithm (VNE-Greedy) on top of the OpenStack Cloud platform. This thesis also in-cludes extended research into the OpenStack cloud computing system and its associated virtual network embedding strategies. |
PDF Full Text Request