Scheduling tight deadlines for scientific workflows in the cloud

Cloud computing has increasingly become a demand for scientific computations as it provides users with simple access for computation. Commercial clouds are also used for scientific analysis and computation because of their scalability, latest high-quality hardware as well as pay-per-use cost model....

Full description

Saved in:

Bibliographic Details
Main Author:	Bajaher, Awadh Salem Saleh
Format:	Thesis
Language:	English
Published:	2018
Subjects:	Cloud Computing
Online Access:	http://psasir.upm.edu.my/id/eprint/69027/1/FSKTM%202018%2054%20-%20IR.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-upm-ir.69027
record_format	uketd_dc
spelling	my-upm-ir.690272019-06-17T01:40:29Z Scheduling tight deadlines for scientific workflows in the cloud 2018-07 Bajaher, Awadh Salem Saleh Cloud computing has increasingly become a demand for scientific computations as it provides users with simple access for computation. Commercial clouds are also used for scientific analysis and computation because of their scalability, latest high-quality hardware as well as pay-per-use cost model. Commercial clouds can be easily accessed globally. There have been several studies presenting new algorithms to generate deadline constrained schedules to minimize the execution cost as well as the high failure rate in schedule constructions. However, there are increased failure rates whenever tight deadlines are produced. The work in this paper focuses on the hurdle of scheduling tight deadline scientific workload. This article will evaluate the performance of the Proportional Deadline Constrained (PDC) algorithm using Cloudsim and compare it with the Deadline Constrained Critical Path (DCCP) scheduling algorithm. The performance evaluation is done using two different performance metrics, success rate and normalized cost. The results show that the PDC performs better in term of success rate metric while the DCCP algorithm has better performance in term of normalized cost metric. The PDC could be improved on the normalized cost. Cloud Computing 2018-07 Thesis http://psasir.upm.edu.my/id/eprint/69027/ http://psasir.upm.edu.my/id/eprint/69027/1/FSKTM%202018%2054%20-%20IR.pdf text en public masters Universiti Putra Malaysia Cloud Computing
institution	Universiti Putra Malaysia
collection	PSAS Institutional Repository
language	English
topic	Cloud Computing
spellingShingle	Cloud Computing Bajaher, Awadh Salem Saleh Scheduling tight deadlines for scientific workflows in the cloud
description	Cloud computing has increasingly become a demand for scientific computations as it provides users with simple access for computation. Commercial clouds are also used for scientific analysis and computation because of their scalability, latest high-quality hardware as well as pay-per-use cost model. Commercial clouds can be easily accessed globally. There have been several studies presenting new algorithms to generate deadline constrained schedules to minimize the execution cost as well as the high failure rate in schedule constructions. However, there are increased failure rates whenever tight deadlines are produced. The work in this paper focuses on the hurdle of scheduling tight deadline scientific workload. This article will evaluate the performance of the Proportional Deadline Constrained (PDC) algorithm using Cloudsim and compare it with the Deadline Constrained Critical Path (DCCP) scheduling algorithm. The performance evaluation is done using two different performance metrics, success rate and normalized cost. The results show that the PDC performs better in term of success rate metric while the DCCP algorithm has better performance in term of normalized cost metric. The PDC could be improved on the normalized cost.
format	Thesis
qualification_level	Master's degree
author	Bajaher, Awadh Salem Saleh
author_facet	Bajaher, Awadh Salem Saleh
author_sort	Bajaher, Awadh Salem Saleh
title	Scheduling tight deadlines for scientific workflows in the cloud
title_short	Scheduling tight deadlines for scientific workflows in the cloud
title_full	Scheduling tight deadlines for scientific workflows in the cloud
title_fullStr	Scheduling tight deadlines for scientific workflows in the cloud
title_full_unstemmed	Scheduling tight deadlines for scientific workflows in the cloud
title_sort	scheduling tight deadlines for scientific workflows in the cloud
granting_institution	Universiti Putra Malaysia
publishDate	2018
url	http://psasir.upm.edu.my/id/eprint/69027/1/FSKTM%202018%2054%20-%20IR.pdf
_version_	1747812659424657408

Scheduling tight deadlines for scientific workflows in the cloud

Similar Items