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

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences. / Heger, Jens; Voß, Thomas.
Proceedings of the 2020 Winter Simulation Conference, WSC 2020. Hrsg. / K.-H. Bae; B. Feng; S. Kim; S. Lazarova-Molnar; Z. Zheng; T. Roeder; R. Thiesing. IEEE - Institute of Electrical and Electronics Engineers Inc., 2020. S. 1608 - 1618 9383903 (Proceedings - Winter Simulation Conference; Band 2020-December).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Heger, J & Voß, T 2020, Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences. in K-H Bae, B Feng, S Kim, S Lazarova-Molnar, Z Zheng, T Roeder & R Thiesing (Hrsg.), Proceedings of the 2020 Winter Simulation Conference, WSC 2020., 9383903, Proceedings - Winter Simulation Conference, Bd. 2020-December, IEEE - Institute of Electrical and Electronics Engineers Inc., S. 1608 - 1618, Winter Simulation Conference 2020, Orlando, USA / Vereinigte Staaten, 14.12.20. https://doi.org/10.1109/WSC48552.2020.9383903

APA

Heger, J., & Voß, T. (2020). Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences. In K.-H. Bae, B. Feng, S. Kim, S. Lazarova-Molnar, Z. Zheng, T. Roeder, & R. Thiesing (Hrsg.), Proceedings of the 2020 Winter Simulation Conference, WSC 2020 (S. 1608 - 1618). Artikel 9383903 (Proceedings - Winter Simulation Conference; Band 2020-December). IEEE - Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC48552.2020.9383903

Vancouver

Heger J, Voß T. Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences. in Bae KH, Feng B, Kim S, Lazarova-Molnar S, Zheng Z, Roeder T, Thiesing R, Hrsg., Proceedings of the 2020 Winter Simulation Conference, WSC 2020. IEEE - Institute of Electrical and Electronics Engineers Inc. 2020. S. 1608 - 1618. 9383903. (Proceedings - Winter Simulation Conference). doi: 10.1109/WSC48552.2020.9383903

Bibtex

@inbook{91c46c919068401cbc21216d68d1cf16,
title = "Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences",
abstract = "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.",
keywords = "Engineering",
author = "Jens Heger and Thomas Vo{\ss}",
year = "2020",
month = dec,
day = "14",
doi = "10.1109/WSC48552.2020.9383903",
language = "English",
series = "Proceedings - Winter Simulation Conference",
publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",
pages = "1608 -- 1618",
editor = "K.-H. Bae and B. Feng and S. Kim and S. Lazarova-Molnar and Z. Zheng and T. Roeder and R. Thiesing",
booktitle = "Proceedings of the 2020 Winter Simulation Conference, WSC 2020",
address = "United States",
note = "Winter Simulation Conference - WSC 2020 : Simulation Drives Innovation, WSC2020 ; Conference date: 14-12-2020 Through 18-12-2020",
url = "http://meetings2.informs.org/wordpress/wsc2020/",

}

RIS

TY - CHAP

T1 - Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences

AU - Heger, Jens

AU - Voß, Thomas

PY - 2020/12/14

Y1 - 2020/12/14

N2 - 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.

AB - 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.

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85103874223&partnerID=8YFLogxK

U2 - 10.1109/WSC48552.2020.9383903

DO - 10.1109/WSC48552.2020.9383903

M3 - Article in conference proceedings

AN - SCOPUS:85103874223

T3 - Proceedings - Winter Simulation Conference

SP - 1608

EP - 1618

BT - Proceedings of the 2020 Winter Simulation Conference, WSC 2020

A2 - Bae, K.-H.

A2 - Feng, B.

A2 - Kim, S.

A2 - Lazarova-Molnar, S.

A2 - Zheng, Z.

A2 - Roeder, T.

A2 - Thiesing, R.

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - Winter Simulation Conference - WSC 2020

Y2 - 14 December 2020 through 18 December 2020

ER -

DOI

Zuletzt angesehen

Aktivitäten

  1. Artificial Intelligence, Human Expertise: the Case of Provenance Linked Open Data
  2. The Influence of Robots’ Emotion Expressions on the Uncanny-Valley-Effect
  3. Reforming from Within : Lessons of Institutional Transformation in a Climate of Systemic Change
  4. Comparison of Two Panel Cointegration Tests
  5. Identification and characterization of coherent behavior in flows
  6. Intra-firm Wage Dispersion and Cost Coverage of Training: Evidence from German Linked Employer-Employee Data
  7. Policy Brief Series
  8. Tracing the Unknown: Learning from Provenance Data
  9. One generation plants the trees, another gets the shade? Negotiators' perceptions and behaviors in intergenerational allocations of resources.
  10. Project-based and other activating strategies and issues of science education - PBE 2021
  11. Determination of Bearing Clearance by the Application of Neural Networks
  12. How does tree sapling diversity influence browsing intensity by deer across spatial scales?
  13. Crazy, Classified City Life - Hackfeminist Future-Making Practices between Dystopia and Utopia, Predictability and Possibility
  14. Projektabschlusspräsentation
  15. PhD Workshop on Theories in Information Systems Science
  16. Inter- and Transdisciplinary Learning
  17. Linking EFL Tasks to the World Outside: Promoting Community-Based Learning and Learner Agency through Blended-Learning Projects
  18. CyberKant, a Timely Response to the Eclipse of Reason by Mechanical Rationality - 2020
  19. PRIORITIZATION OF VETERINARY ANTIBIOTICS FOR ENVIRONMENTAL ANALYSIS USING A SIMPLE SCREENING APPROACH

Publikationen

  1. A two-stage Kalman estimator for motion control using model predictive strategy
  2. Industrial applications using wavelet packets for gross error detection
  3. Introduction
  4. Octanol-Water Partition Coefficient Measurement by a Simple 1H NMR Method
  5. Processing of CSR communication: insights from the ELM
  6. A Lyapunov based PI controller with an anti-windup scheme for a purification process of potable water
  7. Logistical Potentials of Load Balancing via the Build-up and Reduction of Stock
  8. Global fern and lycophyte richness explained: How regional and local factors shape plot richness
  9. Recent Advances in Intelligent Algorithms for Fault Detection and Diagnosis
  10. The role of spatial ability when fostering mental animation in multimedia learning
  11. Ecologies of Making
  12. Water quantity and quality dynamics of the THC - Tuyamuyun hydroengineering complex - and implications for reservoir operation
  13. Modeling High Aswan Dam Reservoir Morphology Using Remote Sensing to Reduce Evaporation
  14. Adaptive control of the nonlinear dynamic behavior of the cantilever-sample system of an atomic force microscope
  15. Saving (in) a common world
  16. 8th challenge on question answering over linked data (QALD-8)
  17. Detection of oscillations with application in the pantograph control
  18. Multi-Professional Support
  19. Use of design methods, team leaders' goal orientation, and team effectiveness: A follow-up study in software development projects
  20. Foreword to applied data science, demo, and nectar tracks
  21. Multiple
  22. Performance of methods to select landscape metrics for modelling species richness
  23. “Circuits of Commons”: Exploring the Connections Between Economic Lives and the Commons
  24. FaQuAD
  25. Recurring patterns and blueprints of industrial symbioses as structural units for an it tool
  26. Simon Denny
  27. Disentangling trade-offs and synergies around ecosystem services with the influence network framework
  28. New developments in extrusion of profiles with variable curvatures and cross-sections
  29. Development and application of a simplified sampling method for volatile polyfluorinated alkyl substances in indoor and environmental air
  30. Robust Decoupling Control of Contact Forces in Robotic Manipulation