A workflow scheduling technique using genetic algorithm in spot instance-based cloud

Daeyong Jung, Taeweon Suh, Heonchang Yu, Joonmin Gil

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users’ job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users’ budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06%. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.

Original languageEnglish
Pages (from-to)3126-3145
Number of pages20
JournalKSII Transactions on Internet and Information Systems
Volume8
Issue number9
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Cloud computing
Genetic algorithms
Scheduling
Costs

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

A workflow scheduling technique using genetic algorithm in spot instance-based cloud. / Jung, Daeyong; Suh, Taeweon; Yu, Heonchang; Gil, Joonmin.

In: KSII Transactions on Internet and Information Systems, Vol. 8, No. 9, 01.01.2014, p. 3126-3145.

Research output: Contribution to journalArticle

@article{19532800d63a4c2794279a6546a50450,
title = "A workflow scheduling technique using genetic algorithm in spot instance-based cloud",
abstract = "Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users’ job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users’ budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06{\%}. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.",
keywords = "Cloud computing, Fault tolerance, Genetic algorithm, Price history, Spot instances, Workflow",
author = "Daeyong Jung and Taeweon Suh and Heonchang Yu and Joonmin Gil",
year = "2014",
month = "1",
day = "1",
doi = "10.3837/tiis.2014.09.010",
language = "English",
volume = "8",
pages = "3126--3145",
journal = "KSII Transactions on Internet and Information Systems",
issn = "1976-7277",
publisher = "Korea Society of Internet Information",
number = "9",

}

TY - JOUR

T1 - A workflow scheduling technique using genetic algorithm in spot instance-based cloud

AU - Jung, Daeyong

AU - Suh, Taeweon

AU - Yu, Heonchang

AU - Gil, Joonmin

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users’ job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users’ budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06%. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.

AB - Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users’ job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users’ budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06%. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.

KW - Cloud computing

KW - Fault tolerance

KW - Genetic algorithm

KW - Price history

KW - Spot instances

KW - Workflow

UR - http://www.scopus.com/inward/record.url?scp=84908046777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908046777&partnerID=8YFLogxK

U2 - 10.3837/tiis.2014.09.010

DO - 10.3837/tiis.2014.09.010

M3 - Article

VL - 8

SP - 3126

EP - 3145

JO - KSII Transactions on Internet and Information Systems

JF - KSII Transactions on Internet and Information Systems

SN - 1976-7277

IS - 9

ER -