Heuristic Dynamic Workflow Scheduling
Author/Presenter
Event Type
Workshop
TimeMonday, November 13th3:30pm -
3:40pm
Location501
DescriptionThe advantages of cloud computing including elastic, on
demand, and pay per use instances, provide an ideal
model for resourcing large scale state-of-the-art
scientific analyses. Large scale scientific experiments
are typically represented as workflows and are the
common model for characterizing escience experiments and
data analytics. Hosting and managing scientific
applications on the cloud poses new challenges in terms
of workflow scheduling which is key in leveraging cloud
benefits. Prior research has studied static scheduling
when the number of workflows is known in advance and all
are submitted at the same time. However, in practice, a
scheduler may have to schedule an unpredictable stream
of workflows. In this paper, we present a new algorithm,
Dynamic Workload Scheduler (DWS). Our algorithm
addresses scheduling of multiple workflows with the aim
of satisfying the deadline for each workflow in a
typical cloud environment in which workflows can be
submitted at any time. Our results show that the DWS
algorithm achieves an average 10% higher success rate in
terms of fulfilling deadlines for different workloads
and reduces the overall cost by an average 23% when
compared to the most recent comparable algorithm.
Author/Presenter
