A task scheduling method after clustering for data intensive jobs in heterogeneous distributed systems

Kazuo Hajikano, Hidehiro Kanemitsu, Moo Wan Kim, Hee Dong Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Several task clustering heuristics are proposed for allocating tasks in heterogeneous systems to achieve a good response time in data intensive jobs. However, one of the challenging problems is the process in task scheduling after task allocation by task clustering. We propose a task scheduling method after task clustering, leveraging worst schedule length (WSL) as an upper bound of the schedule length. In our proposed method, a task in a WSL sequence is scheduled preferentially to make the WSL smaller. Experimental results by simulation show that the response time is improved in several task clustering heuristics. In particular, our proposed scheduling method with the task clustering outperforms conventional list-based task scheduling methods.

Original languageEnglish
Pages (from-to)9-20
Number of pages12
JournalJournal of Computing Science and Engineering
Volume10
Issue number1
DOIs
Publication statusPublished - 2016 Mar 1

Fingerprint

Scheduling

Keywords

  • Data intensive
  • Eterogeneous
  • Task clustering
  • Task scheduling

ASJC Scopus subject areas

  • Computer Science Applications
  • Engineering(all)

Cite this

A task scheduling method after clustering for data intensive jobs in heterogeneous distributed systems. / Hajikano, Kazuo; Kanemitsu, Hidehiro; Kim, Moo Wan; Kim, Hee Dong.

In: Journal of Computing Science and Engineering, Vol. 10, No. 1, 01.03.2016, p. 9-20.

Research output: Contribution to journalArticle

Hajikano, Kazuo ; Kanemitsu, Hidehiro ; Kim, Moo Wan ; Kim, Hee Dong. / A task scheduling method after clustering for data intensive jobs in heterogeneous distributed systems. In: Journal of Computing Science and Engineering. 2016 ; Vol. 10, No. 1. pp. 9-20.
@article{653bfc8ccafd45faa1eff48f12de5132,
title = "A task scheduling method after clustering for data intensive jobs in heterogeneous distributed systems",
abstract = "Several task clustering heuristics are proposed for allocating tasks in heterogeneous systems to achieve a good response time in data intensive jobs. However, one of the challenging problems is the process in task scheduling after task allocation by task clustering. We propose a task scheduling method after task clustering, leveraging worst schedule length (WSL) as an upper bound of the schedule length. In our proposed method, a task in a WSL sequence is scheduled preferentially to make the WSL smaller. Experimental results by simulation show that the response time is improved in several task clustering heuristics. In particular, our proposed scheduling method with the task clustering outperforms conventional list-based task scheduling methods.",
keywords = "Data intensive, Eterogeneous, Task clustering, Task scheduling",
author = "Kazuo Hajikano and Hidehiro Kanemitsu and Kim, {Moo Wan} and Kim, {Hee Dong}",
year = "2016",
month = "3",
day = "1",
doi = "10.5626/JCSE.2016.10.1.9",
language = "English",
volume = "10",
pages = "9--20",
journal = "Journal of Computing Science and Engineering",
issn = "1976-4677",
publisher = "Korean Institute of Information Scientists and Engineers",
number = "1",

}

TY - JOUR

T1 - A task scheduling method after clustering for data intensive jobs in heterogeneous distributed systems

AU - Hajikano, Kazuo

AU - Kanemitsu, Hidehiro

AU - Kim, Moo Wan

AU - Kim, Hee Dong

PY - 2016/3/1

Y1 - 2016/3/1

N2 - Several task clustering heuristics are proposed for allocating tasks in heterogeneous systems to achieve a good response time in data intensive jobs. However, one of the challenging problems is the process in task scheduling after task allocation by task clustering. We propose a task scheduling method after task clustering, leveraging worst schedule length (WSL) as an upper bound of the schedule length. In our proposed method, a task in a WSL sequence is scheduled preferentially to make the WSL smaller. Experimental results by simulation show that the response time is improved in several task clustering heuristics. In particular, our proposed scheduling method with the task clustering outperforms conventional list-based task scheduling methods.

AB - Several task clustering heuristics are proposed for allocating tasks in heterogeneous systems to achieve a good response time in data intensive jobs. However, one of the challenging problems is the process in task scheduling after task allocation by task clustering. We propose a task scheduling method after task clustering, leveraging worst schedule length (WSL) as an upper bound of the schedule length. In our proposed method, a task in a WSL sequence is scheduled preferentially to make the WSL smaller. Experimental results by simulation show that the response time is improved in several task clustering heuristics. In particular, our proposed scheduling method with the task clustering outperforms conventional list-based task scheduling methods.

KW - Data intensive

KW - Eterogeneous

KW - Task clustering

KW - Task scheduling

UR - http://www.scopus.com/inward/record.url?scp=85008254184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008254184&partnerID=8YFLogxK

U2 - 10.5626/JCSE.2016.10.1.9

DO - 10.5626/JCSE.2016.10.1.9

M3 - Article

AN - SCOPUS:85008254184

VL - 10

SP - 9

EP - 20

JO - Journal of Computing Science and Engineering

JF - Journal of Computing Science and Engineering

SN - 1976-4677

IS - 1

ER -