CLOUD-BASED FLOWBSTER PORTAL TO DESIGN AND DEPLOY SCIENTIFIC WORKFLOWS

Abstract

A workflow system called Flowbster has been designed to create efficient data pipelines in clouds. The entire Flowbster workflow is dynamically built by using virtual machines on a target cloud. The paper describes a recently designed and developed web-based science gateway to support Flowbster. It provides a high-level graphical environment to handle different levels of abstractions, like workflows representing the layout and deployment representing the infrastructure realizing the workflow. Detailed overview of the user interface, the portal architecture and its internal operation are given in the paper. Moreover, an insight is provided on the selection and cooperation of the web modules and on the integration of the portal in the firebase environment developed by Google.