Smart Manufacturing Scheduling with Edge Computing Using Multiclass Deep Q Network

Chun Cheng Lin, Der-Jiunn Deng, Yen Ling Chih, Hsin Ting Chiu

Research output: Contribution to journalArticle

Abstract

Manufacturing is involved with complex job shop scheduling problems (JSP). In smart factories, edge computing supports computing resources at the edge of production in a distributed way to reduce response time of making production decisions. However, most works on JSP did not consider edge computing. Therefore, this paper proposes a smart manufacturing factory framework based on edge computing, and further investigates the JSP under such a framework. With recent success of some AI applications, the deep Q network (DQN), which combines deep learning and reinforcement learning, has showed its great computing power to solve complex problems. Therefore, we adjust the DQN with an edge computing framework to solve the JSP. Different from the classical DQN with only one decision, this paper extends the DQN to address the decisions of multiple edge devices. Simulation results show that the proposed method performs better than the other methods using only one dispatching rule.

Original languageEnglish
Article number8676376
Pages (from-to)4276-4284
Number of pages9
JournalIEEE Transactions on Industrial Informatics
Volume15
Issue number7
DOIs
Publication statusPublished - 2019 Jul 1

Fingerprint

Scheduling
Industrial plants
Reinforcement learning
Job shop scheduling

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Lin, Chun Cheng ; Deng, Der-Jiunn ; Chih, Yen Ling ; Chiu, Hsin Ting. / Smart Manufacturing Scheduling with Edge Computing Using Multiclass Deep Q Network. In: IEEE Transactions on Industrial Informatics. 2019 ; Vol. 15, No. 7. pp. 4276-4284.
@article{909530a0034740ea97d72a7f0ec51229,
title = "Smart Manufacturing Scheduling with Edge Computing Using Multiclass Deep Q Network",
abstract = "Manufacturing is involved with complex job shop scheduling problems (JSP). In smart factories, edge computing supports computing resources at the edge of production in a distributed way to reduce response time of making production decisions. However, most works on JSP did not consider edge computing. Therefore, this paper proposes a smart manufacturing factory framework based on edge computing, and further investigates the JSP under such a framework. With recent success of some AI applications, the deep Q network (DQN), which combines deep learning and reinforcement learning, has showed its great computing power to solve complex problems. Therefore, we adjust the DQN with an edge computing framework to solve the JSP. Different from the classical DQN with only one decision, this paper extends the DQN to address the decisions of multiple edge devices. Simulation results show that the proposed method performs better than the other methods using only one dispatching rule.",
author = "Lin, {Chun Cheng} and Der-Jiunn Deng and Chih, {Yen Ling} and Chiu, {Hsin Ting}",
year = "2019",
month = "7",
day = "1",
doi = "10.1109/TII.2019.2908210",
language = "English",
volume = "15",
pages = "4276--4284",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "7",

}

Smart Manufacturing Scheduling with Edge Computing Using Multiclass Deep Q Network. / Lin, Chun Cheng; Deng, Der-Jiunn; Chih, Yen Ling; Chiu, Hsin Ting.

In: IEEE Transactions on Industrial Informatics, Vol. 15, No. 7, 8676376, 01.07.2019, p. 4276-4284.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Smart Manufacturing Scheduling with Edge Computing Using Multiclass Deep Q Network

AU - Lin, Chun Cheng

AU - Deng, Der-Jiunn

AU - Chih, Yen Ling

AU - Chiu, Hsin Ting

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Manufacturing is involved with complex job shop scheduling problems (JSP). In smart factories, edge computing supports computing resources at the edge of production in a distributed way to reduce response time of making production decisions. However, most works on JSP did not consider edge computing. Therefore, this paper proposes a smart manufacturing factory framework based on edge computing, and further investigates the JSP under such a framework. With recent success of some AI applications, the deep Q network (DQN), which combines deep learning and reinforcement learning, has showed its great computing power to solve complex problems. Therefore, we adjust the DQN with an edge computing framework to solve the JSP. Different from the classical DQN with only one decision, this paper extends the DQN to address the decisions of multiple edge devices. Simulation results show that the proposed method performs better than the other methods using only one dispatching rule.

AB - Manufacturing is involved with complex job shop scheduling problems (JSP). In smart factories, edge computing supports computing resources at the edge of production in a distributed way to reduce response time of making production decisions. However, most works on JSP did not consider edge computing. Therefore, this paper proposes a smart manufacturing factory framework based on edge computing, and further investigates the JSP under such a framework. With recent success of some AI applications, the deep Q network (DQN), which combines deep learning and reinforcement learning, has showed its great computing power to solve complex problems. Therefore, we adjust the DQN with an edge computing framework to solve the JSP. Different from the classical DQN with only one decision, this paper extends the DQN to address the decisions of multiple edge devices. Simulation results show that the proposed method performs better than the other methods using only one dispatching rule.

UR - http://www.scopus.com/inward/record.url?scp=85068618692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068618692&partnerID=8YFLogxK

U2 - 10.1109/TII.2019.2908210

DO - 10.1109/TII.2019.2908210

M3 - Article

VL - 15

SP - 4276

EP - 4284

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 7

M1 - 8676376

ER -