Multi objective dynamic job shop scheduling using composite dispatching rule and reinforcement learning

Xili Chen, Hao Wen Lin, Xin Chang Hao, Tomohiro Murata

Research output: Contribution to journalArticle

Abstract

The applications of composite dispatching rules for multi objective dynamic scheduling have been widely studied in literature. In general, a composite dispatching rule is a combination of several elementary dispatching rules, which is designed to optimize multiple objectives of interest under a certain scheduling environment. The relative importance of elementary dispatching rules is modeled by weight factors. A critical issue for implementation of composite dispatching rule is that the inappropriate weight values may result in poor performance. This paper presents an offline scheduling knowledge acquisition method based on reinforcement learning using simulation technique. The scheduling knowledge is applied to adjust the appropriate weight values of elementary dispatching rules in composite manner with respect to work in process fluctuation of machines during online scheduling. Implementation of the proposed method in a two objectives dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

Original languageEnglish
Pages (from-to)1241-1249
Number of pages9
JournalIEEJ Transactions on Electronics, Information and Systems
Volume131
Issue number6
DOIs
Publication statusPublished - 2011

Fingerprint

Reinforcement learning
Scheduling
Composite materials
Knowledge acquisition
Job shop scheduling

Keywords

  • Composite dispatching rule
  • Dynamic job shop
  • Multi objective scheduling
  • Reinforcement learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Multi objective dynamic job shop scheduling using composite dispatching rule and reinforcement learning. / Chen, Xili; Lin, Hao Wen; Hao, Xin Chang; Murata, Tomohiro.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 131, No. 6, 2011, p. 1241-1249.

Research output: Contribution to journalArticle

@article{90921e6dceb2437d882c1a8c57c672ad,
title = "Multi objective dynamic job shop scheduling using composite dispatching rule and reinforcement learning",
abstract = "The applications of composite dispatching rules for multi objective dynamic scheduling have been widely studied in literature. In general, a composite dispatching rule is a combination of several elementary dispatching rules, which is designed to optimize multiple objectives of interest under a certain scheduling environment. The relative importance of elementary dispatching rules is modeled by weight factors. A critical issue for implementation of composite dispatching rule is that the inappropriate weight values may result in poor performance. This paper presents an offline scheduling knowledge acquisition method based on reinforcement learning using simulation technique. The scheduling knowledge is applied to adjust the appropriate weight values of elementary dispatching rules in composite manner with respect to work in process fluctuation of machines during online scheduling. Implementation of the proposed method in a two objectives dynamic job shop scheduling problem is demonstrated and the results are satisfactory.",
keywords = "Composite dispatching rule, Dynamic job shop, Multi objective scheduling, Reinforcement learning",
author = "Xili Chen and Lin, {Hao Wen} and Hao, {Xin Chang} and Tomohiro Murata",
year = "2011",
doi = "10.1541/ieejeiss.131.1241",
language = "English",
volume = "131",
pages = "1241--1249",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "6",

}

TY - JOUR

T1 - Multi objective dynamic job shop scheduling using composite dispatching rule and reinforcement learning

AU - Chen, Xili

AU - Lin, Hao Wen

AU - Hao, Xin Chang

AU - Murata, Tomohiro

PY - 2011

Y1 - 2011

N2 - The applications of composite dispatching rules for multi objective dynamic scheduling have been widely studied in literature. In general, a composite dispatching rule is a combination of several elementary dispatching rules, which is designed to optimize multiple objectives of interest under a certain scheduling environment. The relative importance of elementary dispatching rules is modeled by weight factors. A critical issue for implementation of composite dispatching rule is that the inappropriate weight values may result in poor performance. This paper presents an offline scheduling knowledge acquisition method based on reinforcement learning using simulation technique. The scheduling knowledge is applied to adjust the appropriate weight values of elementary dispatching rules in composite manner with respect to work in process fluctuation of machines during online scheduling. Implementation of the proposed method in a two objectives dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

AB - The applications of composite dispatching rules for multi objective dynamic scheduling have been widely studied in literature. In general, a composite dispatching rule is a combination of several elementary dispatching rules, which is designed to optimize multiple objectives of interest under a certain scheduling environment. The relative importance of elementary dispatching rules is modeled by weight factors. A critical issue for implementation of composite dispatching rule is that the inappropriate weight values may result in poor performance. This paper presents an offline scheduling knowledge acquisition method based on reinforcement learning using simulation technique. The scheduling knowledge is applied to adjust the appropriate weight values of elementary dispatching rules in composite manner with respect to work in process fluctuation of machines during online scheduling. Implementation of the proposed method in a two objectives dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

KW - Composite dispatching rule

KW - Dynamic job shop

KW - Multi objective scheduling

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=80052396211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052396211&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.131.1241

DO - 10.1541/ieejeiss.131.1241

M3 - Article

AN - SCOPUS:80052396211

VL - 131

SP - 1241

EP - 1249

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 6

ER -