Title
Towards Scalable and Cost-aware Bioinformatics Workflow Execution in the Cloud-Recent Advances to the Tavaxy Workflow System
Abstract
Cloud-based scientific workflow systems can play an important role in the development of cost effective bioinformatics analysis applications. So far, most efforts for supporting cloud computing in such workflow systems have focused on simply porting them to the cloud environment. The next due steps are to optimize these systems to exploit the advantages of the cloud computing model, basically in terms of managing resource elasticity and the associated business model. In this paper, we introduce new advancements in designing scalable and cost-effective workflows in the cloud using the Tavaxy workflow system, focusing on genome analysis applications. We provide an overview of the system and describe its key cloud features including the configuration and execution of complete workflows and/or specific sub-workflows in the cloud. Taking real world examples, we demonstrate the key elasticity management features of the system. These features are designed to support two common scenarios: 1 minimizing workflow execution time under budget constraints and 2 minimizing budget spend under workflow deadline constraints. We evaluate the effectiveness of our approach by conducting experiments on the Amazon EC2 cloud with dynamic pricing and variable heterogeneous resource allocation.
Year
DOI
Venue
2013
10.3233/FI-2013-946
Fundam. Inform.
Keywords
Field
DocType
workflow execution time,workflow system,cost-aware bioinformatics workflow execution,key cloud,cloud environment,tavaxy workflow system,cloud computing,cloud-recent advances,workflow deadline constraint,cloud-based scientific workflow system,cloud computing model,amazon ec2 cloud,towards scalable,bioinformatics
Discrete mathematics,Workflow technology,Computer science,Windows Workflow Foundation,Resource allocation,Workflow engine,Workflow management system,Workflow,Database,Distributed computing,Scalability,Cloud computing
Journal
Volume
Issue
ISSN
128
3
0169-2968
Citations 
PageRank 
References 
1
0.37
19
Authors
3
Name
Order
Citations
PageRank
Mohamed Abouelhoda1955.73
Shady Issa2143.97
Moustafa Ghanem353853.05