Architecting Cloud Workflow: Theory and Practice

摘要: The data scale, science analysis and processing complexity in scientific community are growing exponentially the "big data" era. Cloud computing paradigm has been widely adopted to provide unprecedented scalability resources on demand, while workflow management systems (SWFMSs) have proven essential services computing. Uniting advantages of both cloud SWFMSs can bring a valuable solution problem researchers. Although series work concentrated integrating with platforms that much experience for future research development, study from an architectural perspective is still missing. main contributions this paper are: 1) based comprehensive survey available integration options, we propose service framework computing, 2) implement various validate feasibility proposed framework, 3) conduct set experiments demonstrate capability use NASA MODIS image as showcase implementation.