2017
DOI: 10.1007/978-3-319-64203-1_23
|View full text |Cite
|
Sign up to set email alerts
|

A Simplified Model for Simulating the Execution of a Workflow in Cloud

Abstract: Abstract. Although simulators provide approximate, faster and easier simulation of an application execution in Clouds, still many researchers argue that these results cannot be always generalized for complex application types, which consist of many dependencies among tasks and various scheduling possibilities, such as workflows. DynamicCloudSim, the extension of the well known CloudSim simulator, offers users the capability to simulate the Cloud heterogeneity by introducing noisiness in dozens parameters. Stil… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 22 publications
0
4
0
Order By: Relevance
“…We compared the S TET =FT model with our previous work S TET [8] (which noises TET only), the standard Dynami-cCloudSim model S DCS with its standard heterogeneity parameter values, and the real Cloud experimental results (denoted as C). We implemented both S TET and S TET =FT models in DynamicCloudSim besides its default S DCS model.…”
Section: Simulation Environmentmentioning
confidence: 99%
See 1 more Smart Citation
“…We compared the S TET =FT model with our previous work S TET [8] (which noises TET only), the standard Dynami-cCloudSim model S DCS with its standard heterogeneity parameter values, and the real Cloud experimental results (denoted as C). We implemented both S TET and S TET =FT models in DynamicCloudSim besides its default S DCS model.…”
Section: Simulation Environmentmentioning
confidence: 99%
“…To overcome these deficiencies that lead to an incomplete or inaccurate Cloud simulation setup, we introduced in previous work [8] a simple approach to determine and configure the Cloud performance instability by noising the task execution times. However, many scientific applications, such as workflows, are data intensive and spend up to 90 percent of their makespan on file transfers [9].…”
Section: Introductionmentioning
confidence: 99%
“…Several algorithms have been proposed from traditional scheduling algorithms (HEFT, 28 Min–Min, Max–Min, etc. ), to more complex algorithms that consider performance prediction, 29‐31 multisite clouds, 32 and so on. These algorithms have to be implemented in a scheduler component in each WfMS.…”
Section: Introductionmentioning
confidence: 99%
“…Although there are some approaches that aim at proposing performance models for VM live migrations and interference, 33 there is no definitive solution. In fact, depending on the type of interference it is difficult, or sometimes even impossible, to model all these characteristics because they are usually provider‐ and application‐dependent 30 . Estimating activations performance in VMs is also a difficult task to accomplish.…”
Section: Introductionmentioning
confidence: 99%