Information Technology Reference
In-Depth Information
Instance-Intensive Cost-Constrained Workflows Scheduling Algorithm in a Cloud
Mukute et al. [10] proposed an algorithm based on Job Shop to solve the issue of
dynamic scheduling in cloud computing with a special attention to the case of in-
stance-intensive cost-constrained workflows. They first consider the classification and
combinatorial optimization of the concurrent tasks which need specified resources
with a certain number. Then they specify the priority for tasks and make user minim-
ize the overall cost in the end.
Meeting Deadlines of Scientific Workflows with Tasks Replication
In order to address limitations of ignoring costs related to utilization of the infrastruc-
ture and he capacity of taking advantage of elastic infrastructures and other. Rodrigo
N. Calheiros and Rajkumar Buyya [17] proposed an algorithm, called EIPR, which
uses idle time of provisioned resources to replicate workflow tasks in order to miti-
gate effects of performance variation of resources so that the soft deadlines can be
met. The experiment result showed that the EIPR algorithm increases the chance of
deadlines being met and reduces the total execution time of workflow.
Multi-objective Optimization Workflow Scheduling Algorithms
Multi-objective Workflow Scheduling
Juan et al. proposed [11] a multi-objective workflow scheduling method called Multi-
Objective Heterogeneous Earliest Finish Time (MOHEFT) for multi-objective opti-
mization problem in Amazon EC2 Cloud which offer heterogeneous types of
resources at different prices and with different performance. MOHEFT is a Pareto-
based list scheduling heuristic that provides the user with a set of tradeoff optimal
solutions from which the one that better suits the user requirements can be manually
selected. Finally, the experiments revealed that MOHEFT was able to meet the con-
straints imposed by current commercial Clouds in terms of the maximum amount of
Minimum Total Cost Under User-Designated Total Deadline Algorithm
Jing Yan et al. [8] proposed a scheduling algorithm, named Minimum Total Cost Un-
der User-designated Total Deadline (MCUD), based on multiple instances. For the
workflow instances of the same type, after classification, MCUD algorithm distributes
the user-designated overall deadline into each task with a new distribution method. In
addition MCUD algorithm adjusts the sub-deadline of successive task dynamically
during the scheduling process. Instances of the same nature are given the sub-deadline
distribution results of some difference, which can avoid the fierce competition of
cheaper services and increase the efficiency of resource utilization.
Auto-Scaling to Minimize Cost and Meet Application Deadlines
Ming Mao [14] et al. proposed a new auto-scaling mechanism for deadline to avoid
the faults which the traditional “auto-scaling” mechanisms only support simple re-
source utilization indicators and do not specifically consider both user performance
requirements and budget concerns. What the auto-scaling mechanism they have
Search WWH ::

Custom Search