Towards End-to-End Application Slicing in Multi-access Edge Computing systems: Architecture Discussion and Proof-of-Concept

The network slice framework is one of 5G important pillars. It allows for sharing a 5G infrastructure among different tenants leading to communication cost reduction. Concurrently, the introduction of the Multi-access Edge Computing (MEC) into 5G to support time-critical applications raises the need for integrating this cloud infrastructure to the aforementioned framework. Indeed, end-to-end latency guarantee requires the management of end-to-end slice latency-related resources. For this purpose, this paper proposes a complete and sensible MEC slicing architecture including the overall management hierarchy after revealing gaps in the state-of-the-art with regards to such objective. New concepts and new architecture extensions are discussed and provided. A concrete implementation of the proposed architectures focusing on the MEC domain is also provided together with slice isolation performance tests.