Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Sequencing operations can be difficult, especially under uncertain conditions. Applying decentral sequencing rules has been a viable option; however, no rule exists that can outperform all other rules under varying system performance. For this reason, reinforcement learning (RL) is used as a hyper heuristic to select a sequencing rule based on the system status. Based on multiple training scenarios considering stochastic influences, such as varying inter arrival time or customers changing the product mix, the advantages of RL are presented. For evaluation, the trained agents are exploited in a generic manufacturing system. The best agent trained is able to dynamically adjust sequencing rules based on system performance, thereby matching and outperforming the presumed best static sequencing rules by ~ 3%. Using the trained policy in an unknown scenario, the RL heuristic is still able to change the sequencing rule according to the system status, thereby providing a robust performance.
Translated title of the contributionDynamische Auswahl von Reihenfolgeregeln mit bestärkendem Lernen in einer Werkstattfertigung mit stochastischen Einflüssen
Original languageEnglish
Title of host publicationProceedings of the 2020 Winter Simulation Conference, WSC 2020
EditorsK.-H. Bae, B. Feng, S. Kim, S. Lazarova-Molnar, Z. Zheng, T. Roeder, R. Thiesing
Number of pages11
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date14.12.2020
Pages1608 - 1618
Article number9383903
ISBN (electronic)978-1-7281-9499-8
DOIs
Publication statusPublished - 14.12.2020
EventWinter Simulation Conference - WSC 2020: Simulation Drives Innovation - Orlando, United States
Duration: 14.12.202018.12.2020
http://meetings2.informs.org/wordpress/wsc2020/

Recently viewed

Activities

  1. Methods and Methodologies for Researching Globalization and Development - 2015
  2. Learning to rate player actions in multi-agent scenarios
  3. Preliminary selection of experimental techniques in Subtask D
  4. The semantics of transformation: conceptual work based on Freirean methodology.
  5. Exploring Affective Human-Robot Interaction with Movie Scenes
  6. International Symposium on Multiscale Computational Analysis of Complex Materials
  7. Co-Supervisor for the Dissertation "The effects of forest structural element retention on insect communities"
  8. Co-supervisor of the dissertation "Multi-trophic interactions and functional diversity in biodiversity experiments."
  9. Methods of boundary work for inter- and transdisciplinary research.
  10. DIY Bat Detector with Gamification Elements
  11. Digitalization and cross-border knowledge transfer: The impact on international assignments
  12. Learning to Rate Player Actions on the Example of Soccer
  13. Using Gamification Elements as a tool for species protection awareness (Single Paper)
  14. Mutual Learning and Knowledge Integration in Transdisciplinary Development Teams: Empirical Findings about a Collaborative Format in Teacher Education
  15. Strengthening Form-Focused Practice in Task-Based Language Teaching Through Intelligent CALL (EUROCALL)
  16. Foresters understanding of forest nature and its gender
  17. Using the Method of Limits to Assess Comfortable Time Headways in Adaptive Cruise Control
  18. Strategies for the Control of Water Treatment by Stripping and Injection of CO2
  19. DIY-Fledermausdetektor mit Gamification-Elementen
  20. Preliminary results of the state of the art study on scaling and corrosion.
  21. Eigenzeiten of Creativity – Temporal Work as a Coordination Challenge in Artistic and Scientific Project Ecologies

Prizes

  1. Transferpreis

Publications

  1. The Use of Factorization and Multimode Parametric Spectra in Estimating Frequency and Spectral Parameters of Signal
  2. Robust Flatness Based Control of an Electromagnetic Linear Actuator Using Adaptive PID Controller
  3. Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning
  4. Simulation based comparison of safety-stock calculation methods
  5. Modeling of lateness distributions depending on the sequencing method with respect to productivity effects
  6. A Lean Convolutional Neural Network for Vehicle Classification
  7. Editorial: Machine Learning and Data Mining in Materials Science
  8. Computing regression statistics from grouped data
  9. Understanding the error-structure of Time-driven Activity-based Costing
  10. Managing (in) times of uncertainty
  11. Optimising business performance with standard software systems
  12. Self-perception of the internal audit function within the corporate governance system - Empirical evidence for the European Union
  13. Recontextualizing Anthropomorphic Metaphors in Organization Studies
  14. Study of fuzzy controllers performance
  15. Quantification of amino acids in fermentation media by isocratic HPLC analysis of their
  16. Fusion of knowledge bases for better navigation of wheeled mobile robotic group with 3D TVS
  17. Simulation of SARS-CoV-2 pandemic in Germany with ordinary differential equations in MATLAB
  18. Validity claims in context
  19. Attention and the Speed of Information Processing
  20. Fermentative utilization of coffee mucilage using Bacillus coagulans and investigation of down-stream processing of fermentation broth for optically pure L(+)-lactic acid production
  21. Non-acceptances in context
  22. Citizen Action in the Time of the Network
  23. Numerical Investigation of the Effect of Rolling on the Localized Stress and Strain Induction for Wire + Arc Additive Manufactured Structures
  24. Mapping the Order of New Migration
  25. The pace of range expansion