Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling

Kuo Hao Ho; Ji Han Wu; Fan Chiang; Yuan Yu Wu; Sheng I. Chen; Ted Kuo; Feng Jian Wang; I. Chen Wu

doi:10.1109/ICCE-Taiwan58799.2023.10226873

Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling

Kuo Hao Ho, Ji Han Wu, Fan Chiang, Yuan Yu Wu, Sheng I. Chen, Ted Kuo, Feng Jian Wang, I. Chen Wu^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Recently, deep reinforcement learning (DRL) methods attract much attention for solving job-shop scheduling problem (JSP), a NP-hard optimization problem. One of DRL methods is based on priority dispatching rules (PDRs), which is easy to be implemented, to dispatch operations to machines. In this paper, we propose a graph neural network (GNN) to enhance Luo's method [1] to choose a PDR to dispatch. With GNN, our method, trained with small JSP problems, also performs well in large JSP problems. Our experiments show that our method outperforms PDR methods and most of other DRL methods, particularly for large JSP problems.

Original language	English
Title of host publication	2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	805-806
Number of pages	2
ISBN (Electronic)	9798350324174
DOIs	https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226873
State	Published - 2023
Event	2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Pingtung, Taiwan Duration: 17 Jul 2023 → 19 Jul 2023

Publication series

Name	2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings

Conference

Conference	2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023
Country/Territory	Taiwan
City	Pingtung
Period	17/07/23 → 19/07/23

Keywords

neural network applications
scheduling

Access to Document

10.1109/ICCE-Taiwan58799.2023.10226873

Cite this

Ho, K. H., Wu, J. H., Chiang, F., Wu, Y. Y., Chen, S. I., Kuo, T., Wang, F. J., & Wu, I. C. (2023). Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling. In 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings (pp. 805-806). (2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226873

Ho, Kuo Hao ; Wu, Ji Han ; Chiang, Fan et al. / Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling. 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 805-806 (2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings).

@inproceedings{c246748c9f2f43a09371a511bde103e4,

title = "Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling",

abstract = "Recently, deep reinforcement learning (DRL) methods attract much attention for solving job-shop scheduling problem (JSP), a NP-hard optimization problem. One of DRL methods is based on priority dispatching rules (PDRs), which is easy to be implemented, to dispatch operations to machines. In this paper, we propose a graph neural network (GNN) to enhance Luo's method [1] to choose a PDR to dispatch. With GNN, our method, trained with small JSP problems, also performs well in large JSP problems. Our experiments show that our method outperforms PDR methods and most of other DRL methods, particularly for large JSP problems.",

keywords = "neural network applications, scheduling",

author = "Ho, {Kuo Hao} and Wu, {Ji Han} and Fan Chiang and Wu, {Yuan Yu} and Chen, {Sheng I.} and Ted Kuo and Wang, {Feng Jian} and Wu, {I. Chen}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 ; Conference date: 17-07-2023 Through 19-07-2023",

year = "2023",

doi = "10.1109/ICCE-Taiwan58799.2023.10226873",

language = "English",

series = "2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "805--806",

booktitle = "2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings",

address = "美國",

}

Ho, KH, Wu, JH, Chiang, F, Wu, YY, Chen, SI , Kuo, T, Wang, FJ & Wu, IC 2023, Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling. in 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings. 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 805-806, 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023, Pingtung, Taiwan, 17/07/23. https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226873

Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling. / Ho, Kuo Hao; Wu, Ji Han; Chiang, Fan et al.
2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 805-806 (2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling

AU - Ho, Kuo Hao

AU - Wu, Ji Han

AU - Chiang, Fan

AU - Wu, Yuan Yu

AU - Chen, Sheng I.

AU - Kuo, Ted

AU - Wang, Feng Jian

AU - Wu, I. Chen

PY - 2023

Y1 - 2023

N2 - Recently, deep reinforcement learning (DRL) methods attract much attention for solving job-shop scheduling problem (JSP), a NP-hard optimization problem. One of DRL methods is based on priority dispatching rules (PDRs), which is easy to be implemented, to dispatch operations to machines. In this paper, we propose a graph neural network (GNN) to enhance Luo's method [1] to choose a PDR to dispatch. With GNN, our method, trained with small JSP problems, also performs well in large JSP problems. Our experiments show that our method outperforms PDR methods and most of other DRL methods, particularly for large JSP problems.

AB - Recently, deep reinforcement learning (DRL) methods attract much attention for solving job-shop scheduling problem (JSP), a NP-hard optimization problem. One of DRL methods is based on priority dispatching rules (PDRs), which is easy to be implemented, to dispatch operations to machines. In this paper, we propose a graph neural network (GNN) to enhance Luo's method [1] to choose a PDR to dispatch. With GNN, our method, trained with small JSP problems, also performs well in large JSP problems. Our experiments show that our method outperforms PDR methods and most of other DRL methods, particularly for large JSP problems.

KW - neural network applications

KW - scheduling

UR - http://www.scopus.com/inward/record.url?scp=85174907860&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Taiwan58799.2023.10226873

DO - 10.1109/ICCE-Taiwan58799.2023.10226873

M3 - Conference contribution

AN - SCOPUS:85174907860

T3 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings

SP - 805

EP - 806

BT - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

Y2 - 17 July 2023 through 19 July 2023

ER -

Ho KH, Wu JH, Chiang F, Wu YY, Chen SI , Kuo T et al. Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling. In 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 805-806. (2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings). doi: 10.1109/ICCE-Taiwan58799.2023.10226873

Deep Reinforcement Learning Based on Graph Neural Networks for Job-shop Scheduling

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this