Service deployment on multi-access edge computing environments

• Main Author: Santos, David Manuel Ribeiro
• Publication Date: 2018
• Format: Master thesis
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10773/25610
• topic: MEC; SDN; NFV; 5G Networks; Cloud Computing; Fog Computing; Edge; 4G; Virtualization

Driven by the visions of the 5th Generation of Mobile Networks (5G), and with an increasing acceptance of software-based network technologies, such as Network Function Virtualization (NFV) and Software Defined Networks (SDN), a transformation in network infrastructure is presently taking place, along with different requirements in terms of how networks are managed and deployed. One of the significantly changes is a shift in the cloud computing paradigm, moving from a centralized cloud computing towards the edge of the network. This new environment, providing a cloud computing platform at the edge of the network, is referred to as Multi-Acess Edge Computing (MEC). The main feature of MEC is to provide mobile computing, network control and storage to the network edges, enabling computation-intensive and latency-critical applications targeting resource-limited mobile devices. In this thesis a MEC architecture solution is provided, capable of supporting heterogeneous access networks, to assist as a platform for service deployment. Several MEC use case scenarios are evaluated on the proposed scheme, in order to attest the advantages of a MEC deployment. Results show that the proposed environment is significantly faster on performing compute-intensive applications, mainly due to lower end-to-end latency, when compared to traditional centralized cloud servers, translating into energy saving, and reduced backhaul traffic.