Local Search for Deadline Driven Grid Scheduling

D 2007

Local Search for Deadline Driven Grid Scheduling

KLUSÁČEK, Dalibor, Luděk MATYSKA and Hana RUDOVÁ

Basic information

Original name

Local Search for Deadline Driven Grid Scheduling

Name in Czech

Lokální prohledávání pro gridové plánování s termíny dokončení

Authors

KLUSÁČEK, Dalibor (203 Czech Republic), Luděk MATYSKA (203 Czech Republic) and Hana RUDOVÁ (203 Czech Republic, guarantor)

Edition

1. vydání. Brno, Third Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2007), p. 74-81, 8 pp. 2007

Publisher

Ing. Zdeněk Novotný CSc., Ondráčkova 105, 628 00 Brno

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

RIV identification code

RIV/00216224:14330/07:00020506

Organization unit

Faculty of Informatics

ISBN

978-80-7355-077-6

Keywords in English

plánování; Grid; simulátor; lokální prohledávání; Tabu prohledávání

Abstract

ORIG CZ

V originále

This work describes application of local search based algorithms for job scheduling in the Grid environment where dynamic changes occur. The primary intent is to consider problems with the typical quality of service constraint taking into account and minimizing the number of late jobs. To achieve this goal a~special instance of the Tabu search algorithm applicable to dynamic problems is proposed. Also a new dispatching rule generating the initial solution is introduced. Comparison with typical queue-based policies such as First Come First Served, Earliest Deadline First or Easy Backfilling is provided. Experimental results shows that local search based algorithms is a promising technique with better performance than queue-based algorithms while still fast enough to provide solutions in a reasonable time.

In Czech

Práce prezentuje aplikaci lokálního prohledávání na plánování v Gridovém prostředí. Hlavním cílem práce je orientace na problémy s QoS požadavky tak, aby byl minimalizován počet opožděných úloh.

Links

GA201/07/0205, research and development project

Name: Dynamické aspekty rozvrhování

Investor: Czech Science Foundation, Dynamic Aspects of Scheduling

MSM0021622419, plan (intention)

Name: Vysoce paralelní a distribuované výpočetní systémy

Investor: Ministry of Education, Youth and Sports of the CR, Highly Parallel and Distributed Computing Systems

Citovat

KLUSÁČEK, Dalibor, Luděk MATYSKA and Hana RUDOVÁ. Local Search for Deadline Driven Grid Scheduling. In Third Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2007). 1. vydání. Brno: Ing. Zdeněk Novotný CSc., Ondráčkova 105, 628 00 Brno, 2007, p. 74-81. ISBN 978-80-7355-077-6.

@inproceedings{726155,
   author = {Klusáček, Dalibor and Matyska, Luděk and Rudová, Hana},
   address = {Brno},
   booktitle = {Third Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2007)},
   edition = {1. vydání},
   keywords = {plánování; Grid; simulátor; lokální prohledávání; Tabu prohledávání},
   language = {eng},
   location = {Brno},
   isbn = {978-80-7355-077-6},
   pages = {74-81},
   publisher = {Ing. Zdeněk Novotný CSc., Ondráčkova 105, 628 00 Brno},
   title = {Local Search for Deadline Driven Grid Scheduling},
   url = {http://www.fi.muni.cz/~hanka/publ/memics07.pdf},
   year = {2007}
}

TY  - JOUR
ID  - 726155
AU  - Klusáček, Dalibor - Matyska, Luděk - Rudová, Hana
PY  - 2007
TI  - Local Search for Deadline Driven Grid Scheduling
PB  - Ing. Zdeněk Novotný CSc., Ondráčkova 105, 628 00 Brno
CY  - Brno
SN  - 9788073550776
KW  - plánování
KW  - Grid
KW  - simulátor
KW  - lokální prohledávání
KW  - Tabu prohledávání
UR  - http://www.fi.muni.cz/~hanka/publ/memics07.pdf
N2  - This work describes application of local search based algorithms for job scheduling in the Grid environment where dynamic changes occur. The primary intent is to consider problems with the typical quality of service constraint taking into account and minimizing the number of late jobs. To achieve this goal a~special instance of the Tabu search algorithm applicable to dynamic problems is proposed. Also a new dispatching rule generating the initial solution is introduced. Comparison with typical queue-based policies such as First Come First Served, Earliest Deadline First or Easy Backfilling is provided. Experimental results shows that local search based algorithms is a promising technique with better performance than queue-based algorithms while still fast enough to provide solutions in a reasonable time.
ER  -

KLUSÁČEK, Dalibor, Luděk MATYSKA and Hana RUDOVÁ. Local Search for Deadline Driven Grid Scheduling. In \textit{Third Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2007)}. 1. vydání. Brno: Ing. Zdeněk Novotný CSc., Ondráčkova 105, 628 00 Brno, 2007, p.~74-81. ISBN~978-80-7355-077-6.

Detailed Information on Publication Record