Skip to main navigation Skip to search Skip to main content

Dynamic Scheduling Method of Multi-objective Job Shop Based on Reinforcement Learning

  • Zhenwei Zhang*
  • , Lihong Qiao
  • , Zhicheng Huang
  • *Corresponding author for this work
  • China Aerospace Science and Industry Corporation
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Aiming at the dynamic scheduling problem in workshop production, we propose a multi-objective scheduling method. By analyzing the actual dynamic scheduling problem, a mathematical model is constructed. Then the dynamic interference factors in the actual production environment are classified, and the interference intensity and its parameters are designed. On this basis, a dynamic scheduling oriented process model is established by using reinforcement learning and scheduling rules, and the design of its state space, state action value table and reward function is introduced. Finally, the model is trained and we analyze the simulation results of different methods. The results show that the dynamic scheduling method based on reinforcement learning has good performance under different periods and disturbance intensity, which shows this method is effective and feasible for dynamic scheduling problem.

Original languageEnglish
Title of host publicationIntelligent Networked Things - 5th China Conference, CINT 2022, Revised Selected Papers
EditorsLin Zhang, Wensheng Yu, Haijun Jiang, Yuanjun Laili
PublisherSpringer Science and Business Media Deutschland GmbH
Pages510-524
Number of pages15
ISBN (Print)9789811989148
DOIs
StatePublished - 2022
Event5th China Conference on Intelligent Networked Things, CINT 2022 - Virtual, Online
Duration: 7 Aug 20228 Aug 2022

Publication series

NameCommunications in Computer and Information Science
Volume1714 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference5th China Conference on Intelligent Networked Things, CINT 2022
CityVirtual, Online
Period7/08/228/08/22

Keywords

  • Dynamic disturbance
  • Dynamic scheduling
  • Multi-objective
  • Reinforcement learning
  • Scheduling rules

Fingerprint

Dive into the research topics of 'Dynamic Scheduling Method of Multi-objective Job Shop Based on Reinforcement Learning'. Together they form a unique fingerprint.

Cite this