42-48
DEADLINE CONSTRAINED SCIENTIFIC WORKFLOW SCHEDULING WITH RANKING AND REPLICATION OF TASKS
Authors: Nallakumar. R 1, Dr. N. Sengottaiyan 2, Sruthi Priya K.S 3 1Teaching Fellow, 3 PG Scholar Department of CSE, Anna University Regional Centre, Coimbatore, India 1 2 Professor, Depatment of CSE, Indira Institute of Engineering and Technology, Thiruvallur, Chennai, India
Number of views: 465
The emergence of Cloud computing in distributed systems for service provisioning stimulates the
analysts and researchers in executing exploratory scientific applications such as workflows. The most
demanding issues in the Clouds are workflow scheduling, which expects to fulfil the Quality of Service of
the user like a deadline along with the cost reduction of workflow execution. An already prevailing work on
workflow scheduling algorithm is in view of Partial Critical Paths which endeavour’s to reduce the
workflow execution cost and attempts to execute within the user-defined deadline and it is done only in a
single cloud where ample resources won’t be present to fulfil the user demand. In that case cloud providers
will continue to process the user demands in order to increase their revenue. To address this problem, a
novel replication aware dynamic workflow scheduling is introduced to the thought of ranking of tasks along
with task replication for multi cloud and it dynamically allocates the workflows across multiple cloud
domains by satisfying the Quality of Service requirement of the users.