A Multi-Platform Workflow Management System optimized for Cloud Computing Platforms

摘要

The scientific experimentation is facing a data deluge in which the amount of data generated is reaching the order of terabytes per day, and thus huge capacity is required to process this data. Computationally, these processes are modelled using Scientific Workflows. However, the execution of a Scientific Workflow can be a complex and resource-demanding task that must be managed by Workflow Management Systems (WMSs). As new computing paradigms emerge and infrastructures evolve, WMSs are extended to support these new computing back-ends. In fact, in the last years, Cloud Computing has appeared as another viable platform for running scientific applications. However, current WMSs are not optimized to exploit key cloud features. For that reason, this work details the design and implementation of a multi-platform WMS with a novel approach for efficiently supporting cloud resources. The engine has been successfully tested in the execution of a comparative genomics workflow called Orthosearch.