Dynamic Lot Size Optimization with Reinforcement Learning

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

Authors

Production planning and control has a great influence on the economic efficiency and logistical performance of a company. In this context, this article gives an insight into the use of simulation as a virtual model of a filling machine in the process industry. Furthermore, it shows the possibilities of a reinforcement learning (RL) approach for dynamic lot sizing. The contribution indicates a possible implementation in an ERP system and shows how a decision support tool can support the planner to save up to 5% of costs compared to a human planner and a heuristic approach proposed by Groff.

Original languageEnglish
Title of host publicationDynamics in Logistics : Proceedings of the 8th International Conference LDIC 2022, Bremen, Germany
EditorsMichael Freitag, Aseem Kinra, Hebert Kotzab, Nicole Megow
Number of pages10
Place of PublicationCham
PublisherSpringer Science and Business Media B.V.
Publication date01.01.2022
Pages376-385
ISBN (print)978-3-031-05358-0
ISBN (electronic)978-3-031-05359-7
DOIs
Publication statusPublished - 01.01.2022
EventInternational Conference on Dynamics in Logistics - LDIC 2022 - Universität Bremen, Bremen, Germany
Duration: 23.02.202225.02.2022
Conference number: 8
https://www.ldic-conference.org/about-ldic

    Research areas

  • Lot sizing, Reinforcement learning, Simulation
  • Engineering

Recently viewed

Publications

  1. Design and characterization of an EOG signal acquisition system based on the programming of saccadic movement routines
  2. Methodologies for Noise and Gross Error Detection using Univariate Signal-Based Approaches in Industrial Application
  3. Modelling tasks—The relation between linguistic skills, intra-mathematical skills, and context-related prior knowledge
  4. Finding Similar Movements in Positional Data Streams
  5. Multidimensional Cross-Recurrence Quantification Analysis (MdCRQA)–A Method for Quantifying Correlation between Multivariate Time-Series
  6. Lagged Multidimensional Recurrence Quantification Analysis for Determining Leader–Follower Relationships Within Multidimensional Time Series
  7. Mapping interest rate projections using neural networks under cointegration
  8. Switching from a Managing to a Monitoring Function on the Board
  9. Towards a Dynamic Interpretation of Subjective and Objective Values
  10. Performance analysis for loss systems with many subscribers and concurrent services
  11. Using mixture distribution models to test the construct validity of the Physical Self-Description Questionnaire
  12. Effectiveness of a guided multicomponent internet and mobile gratitude training program - A pragmatic randomized controlled trial
  13. Study on the effects of tool design and process parameters on the robustness of deep drawing
  14. A Proposal for Integrating Theories of Complexity for Better Understanding Global Systemic Risks
  15. Model-based logistic controlling of converging material flows
  16. A Cross-Classified CFA-MTMM Model for Structurally Different and Nonindependent Interchangeable Methods
  17. Anomaly detection in formed sheet metals using convolutional autoencoders
  18. Reading and Calculating in Word Problem Solving
  19. Challenges and boundaries in implementing social return on investment
  20. Machine Learning and Knowledge Discovery in Databases
  21. Challenges in detecting proximal effects of existential threat on lie detection accuracy
  22. Lyapunov stability analysis to set up a PI controller for a mass flow system in case of a non-saturating input
  23. »HOW TO MAKE YOUR OWN SAMPLES«
  24. Changing Data Collection Methods Means Different Kind of Data
  25. Design of controllers applied to autonomous unmanned aerial vehicles using software in the loop
  26. Exploration strategies, performance, and error consequences when learning a complex computer task
  27. How, when and why do negotiators use reference points?
  28. There is no Software, there are just Services: Introduction
  29. Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations
  30. Constraint breeds creativity
  31. A computational study of a model of single-crystal strain-gradient viscoplasticity with an interactive hardening relation
  32. Lyapunov Convergence Analysis for Asymptotic Tracking Using Forward and Backward Euler Approximation of Discrete Differential Equations