Comparison and Runtime Adaptation of Cloud Application Topologies based on OCCI

To tackle the cloud provider lock-in, multiple standards have emerged to enable the uniform management of cloud resources across different providers. One of them is the Open Cloud Computing Interface which defines, in addition to a REST API, a metamodel that enables the modelling of cloud resources on different service layers. Even though the standard defines how to manage single cloud resources, no process exists that allows for the automated provisioning of full application topologies and their adaptation at runtime. Therefore, we propose a model-based approach to adapt running cloud application infrastructures, allowing a management on a high abstraction level. Hereby, we check the differences between the runtime- and target state of the topology using a model comparison, matching their resources. Based on this match, we mark each resource indicating required management calls that are systematically executed by an adaptation engine. To show the feasibility of our approach, we evaluate the comparison, as well as the adaptation process on a set of example infrastructures.