Distributed multi-agent learning of objectives for intelligent scheduling

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We use a widely reported dynamic job shop scheduling simulation model that uses multi-agent genetic learning of job scheduling strategies, and extend it to incorporate multiple-conflicting scheduling criteria. Using the modified multiagent genetic learning model, we compare the results of multi-agent learning with the results of different heuristic scheduling rules. The results of our experiments indicate that multi-agent system based scheduling shows better overall performance than any of the individual scheduling rules for multiple conflicting objectives. Several design issues related to further improving the performance of the multi-agent system are investigated.

Original languageEnglish (US)
Pages (from-to)177-203
Number of pages27
JournalInternational Journal of Operations and Quantitative Management
Volume7
Issue number3
StatePublished - Dec 1 2001

Fingerprint

Scheduling
Multi agent systems
Scheduling rules
Multi-agent systems
Experiments
Simulation model
Job shop scheduling
Learning model
Heuristics
Multiple objectives
Experiment

All Science Journal Classification (ASJC) codes

  • Business and International Management
  • Strategy and Management
  • Management Science and Operations Research
  • Information Systems and Management
  • Management of Technology and Innovation

Cite this

@article{5dee584bd3a046238493bb2244d9616d,
title = "Distributed multi-agent learning of objectives for intelligent scheduling",
abstract = "We use a widely reported dynamic job shop scheduling simulation model that uses multi-agent genetic learning of job scheduling strategies, and extend it to incorporate multiple-conflicting scheduling criteria. Using the modified multiagent genetic learning model, we compare the results of multi-agent learning with the results of different heuristic scheduling rules. The results of our experiments indicate that multi-agent system based scheduling shows better overall performance than any of the individual scheduling rules for multiple conflicting objectives. Several design issues related to further improving the performance of the multi-agent system are investigated.",
author = "Pendharkar, {Parag C.}",
year = "2001",
month = "12",
day = "1",
language = "English (US)",
volume = "7",
pages = "177--203",
journal = "International Journal of Operations and Quantitative Management",
issn = "1082-1910",
publisher = "International Forum of Management Scholars (INFOMS)",
number = "3",

}

TY - JOUR

T1 - Distributed multi-agent learning of objectives for intelligent scheduling

AU - Pendharkar, Parag C.

PY - 2001/12/1

Y1 - 2001/12/1

N2 - We use a widely reported dynamic job shop scheduling simulation model that uses multi-agent genetic learning of job scheduling strategies, and extend it to incorporate multiple-conflicting scheduling criteria. Using the modified multiagent genetic learning model, we compare the results of multi-agent learning with the results of different heuristic scheduling rules. The results of our experiments indicate that multi-agent system based scheduling shows better overall performance than any of the individual scheduling rules for multiple conflicting objectives. Several design issues related to further improving the performance of the multi-agent system are investigated.

AB - We use a widely reported dynamic job shop scheduling simulation model that uses multi-agent genetic learning of job scheduling strategies, and extend it to incorporate multiple-conflicting scheduling criteria. Using the modified multiagent genetic learning model, we compare the results of multi-agent learning with the results of different heuristic scheduling rules. The results of our experiments indicate that multi-agent system based scheduling shows better overall performance than any of the individual scheduling rules for multiple conflicting objectives. Several design issues related to further improving the performance of the multi-agent system are investigated.

UR - http://www.scopus.com/inward/record.url?scp=84871463329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871463329&partnerID=8YFLogxK

M3 - Article

VL - 7

SP - 177

EP - 203

JO - International Journal of Operations and Quantitative Management

JF - International Journal of Operations and Quantitative Management

SN - 1082-1910

IS - 3

ER -