[en] There is an increasing interest in extending traditional cloud-native technologies, such as Kubernetes, outside the data center to build a continuum towards the edge and between. However, traditional resource orchestration algorithms do not work well in this case, and it is also difficult to test applications for a heterogeneous cloud infrastructure without actually building it. To address these challenges, we propose a new methodology to aid in deploying, testing, and analyzing the effects of microservice placement and scheduling in a heterogeneous Cloud environment. With this methodology, we can investigate any combination of deployment scenarios and monitor metrics in accordance with the placement of microservices in the cloud-edge continuum. Edge devices may be simulated, but as we use Kubernetes, any device which can be attached to a Kubernetes cluster could be used. In order to demonstrate our methodology, we have applied it to the problem of network function placement of an open-source 5G core implementation.
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SEDAN - Service and Data Management in Distributed Systems
Fonds National de la Recherche - FnR ; Proximus Luxembourg SA
[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SEDAN >]
