PROJECT TITLE :

Supporting Data-Intensive Workflows in Software-Defined Federated Multi-Clouds - 2018

ABSTRACT:

Cloud computing is rising as a viable platform for scientific exploration. Elastic and on-demand access to resources (and different services), the abstraction of “unlimited” resources, and enticing pricing models offer incentives for scientists to move their workflows into clouds. Generalizing these concepts beyond one virtualized datacenter, it's attainable to form federated marketplaces where completely different varieties of resources (e.g., clouds, HPC grids, supercomputers) which will be geographically distributed, are collectively exposed as a single elastic infrastructure. This presents opportunities for optimizing the execution of application workflows with heterogeneous and dynamic necessities, and tackling larger scale problems. In this Project, we have a tendency to introduce a framework to manage the top-to-end execution of knowledge-intensive application workflows in dynamic software-outlined resource federation. This framework enables the autonomic execution of workflows by elastically provisioning an appropriate set of resources that meet application needs, and by adapting this set of resources at runtime as the requirements modification. It conjointly permits users to customise scheduling policies that drive the approach resources federated and used. To demonstrate the advantages of our approach, we tend to study the execution of 2 completely different data-intensive scientific workflows in an exceedingly multi-cloud federation using completely different policies and objective functions.