Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning

Xili Chen, Xinchang Hao, Hao Wen Lin, Tomohiro Murata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

This paper presents a rule driven method of developing composite dispatching rule for multi objective dynamic scheduling. Data envelopment analysis is adopted to select elementary dispatching rules, where each rule is justified as efficient for optimizing specific operational objectives of interest. The selected rules are subsequently combined into a single composite rule using the weighted aggregation manner. An intelligent agent is trained using reinforcement learning to acquire the scheduling knowledge of assigning the appropriate weighting values for building the composite rule to cope with the WIP fluctuation of a machine. Implementation of the proposed method in a two objective dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Automation and Logistics, ICAL 2010
Pages396-401
Number of pages6
DOIs
Publication statusPublished - 2010
Event2010 IEEE International Conference on Automation and Logistics, ICAL 2010 - Shatin
Duration: 2010 Aug 162010 Aug 20

Other

Other2010 IEEE International Conference on Automation and Logistics, ICAL 2010
CityShatin
Period10/8/1610/8/20

Fingerprint

Data envelopment analysis
Reinforcement learning
Scheduling
Composite materials
Intelligent agents
Agglomeration

Keywords

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

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Chen, X., Hao, X., Lin, H. W., & Murata, T. (2010). Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning. In 2010 IEEE International Conference on Automation and Logistics, ICAL 2010 (pp. 396-401). [5585316] https://doi.org/10.1109/ICAL.2010.5585316

Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning. / Chen, Xili; Hao, Xinchang; Lin, Hao Wen; Murata, Tomohiro.

2010 IEEE International Conference on Automation and Logistics, ICAL 2010. 2010. p. 396-401 5585316.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, X, Hao, X, Lin, HW & Murata, T 2010, Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning. in 2010 IEEE International Conference on Automation and Logistics, ICAL 2010., 5585316, pp. 396-401, 2010 IEEE International Conference on Automation and Logistics, ICAL 2010, Shatin, 10/8/16. https://doi.org/10.1109/ICAL.2010.5585316
Chen X, Hao X, Lin HW, Murata T. Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning. In 2010 IEEE International Conference on Automation and Logistics, ICAL 2010. 2010. p. 396-401. 5585316 https://doi.org/10.1109/ICAL.2010.5585316
Chen, Xili ; Hao, Xinchang ; Lin, Hao Wen ; Murata, Tomohiro. / Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning. 2010 IEEE International Conference on Automation and Logistics, ICAL 2010. 2010. pp. 396-401
@inproceedings{d14f04bb899046b4aebcb757343b819e,
title = "Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning",
abstract = "This paper presents a rule driven method of developing composite dispatching rule for multi objective dynamic scheduling. Data envelopment analysis is adopted to select elementary dispatching rules, where each rule is justified as efficient for optimizing specific operational objectives of interest. The selected rules are subsequently combined into a single composite rule using the weighted aggregation manner. An intelligent agent is trained using reinforcement learning to acquire the scheduling knowledge of assigning the appropriate weighting values for building the composite rule to cope with the WIP fluctuation of a machine. Implementation of the proposed method in a two objective dynamic job shop scheduling problem is demonstrated and the results are satisfactory.",
keywords = "Composite dispatching rule, Data envelopment analysis, Dynamic job shop, Multi objective scheduling, Reinforcement learning",
author = "Xili Chen and Xinchang Hao and Lin, {Hao Wen} and Tomohiro Murata",
year = "2010",
doi = "10.1109/ICAL.2010.5585316",
language = "English",
isbn = "9781424483754",
pages = "396--401",
booktitle = "2010 IEEE International Conference on Automation and Logistics, ICAL 2010",

}

TY - GEN

T1 - Rule driven multi objective dynamic scheduling by data envelopment analysis and reinforcement learning

AU - Chen, Xili

AU - Hao, Xinchang

AU - Lin, Hao Wen

AU - Murata, Tomohiro

PY - 2010

Y1 - 2010

N2 - This paper presents a rule driven method of developing composite dispatching rule for multi objective dynamic scheduling. Data envelopment analysis is adopted to select elementary dispatching rules, where each rule is justified as efficient for optimizing specific operational objectives of interest. The selected rules are subsequently combined into a single composite rule using the weighted aggregation manner. An intelligent agent is trained using reinforcement learning to acquire the scheduling knowledge of assigning the appropriate weighting values for building the composite rule to cope with the WIP fluctuation of a machine. Implementation of the proposed method in a two objective dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

AB - This paper presents a rule driven method of developing composite dispatching rule for multi objective dynamic scheduling. Data envelopment analysis is adopted to select elementary dispatching rules, where each rule is justified as efficient for optimizing specific operational objectives of interest. The selected rules are subsequently combined into a single composite rule using the weighted aggregation manner. An intelligent agent is trained using reinforcement learning to acquire the scheduling knowledge of assigning the appropriate weighting values for building the composite rule to cope with the WIP fluctuation of a machine. Implementation of the proposed method in a two objective dynamic job shop scheduling problem is demonstrated and the results are satisfactory.

KW - Composite dispatching rule

KW - Data envelopment analysis

KW - Dynamic job shop

KW - Multi objective scheduling

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=78149420086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149420086&partnerID=8YFLogxK

U2 - 10.1109/ICAL.2010.5585316

DO - 10.1109/ICAL.2010.5585316

M3 - Conference contribution

SN - 9781424483754

SP - 396

EP - 401

BT - 2010 IEEE International Conference on Automation and Logistics, ICAL 2010

ER -