Dispatching rule selection with Gaussian processes

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Authors

Decentralized scheduling with dispatching rules is applied in many fields of logistics and production, especially in highly complex and dynamic scenarios, such as semiconductor manufacturing. Many dispatching rules are proposed in the literature, which perform well on specific scenarios. No rule is known, however, consistently outperforming all other rules. One approach to meet this challenge and improve scheduling performance is to select and switch dispatching rules depending on current system conditions. For this task machine learning techniques (e.g., Artificial Neural Networks) are frequently used. In this paper we investigate the use of a machine learning technique not applied to this task before: Gaussian process regression. Our analysis shows that Gaussian processes predict dispatching rule performance better than Neural Networks in most settings. Additionally, already a single Gaussian Process model can easily provide a measure of prediction quality. This is in contrast to many other machine learning techniques. We show how to use this measure to dynamically add additional training data and incrementally improve the model where necessary. Results therefore suggest, Gaussian processes are a very promising technique, which can lead to better scheduling performance (e.g., reduced mean tardiness) compared to other techniques.

OriginalspracheEnglisch
ZeitschriftCentral European Journal of Operations Research
Jahrgang23
Ausgabenummer1
Seiten (von - bis)235-249
Anzahl der Seiten15
ISSN1435-246X
DOIs
PublikationsstatusErschienen - 03.2015
Extern publiziertJa

DOI

Zuletzt angesehen

Forschende

  1. Goddert Oheimb

Publikationen

  1. Appendix A: Design, implementation, and analysis of the iGOES project
  2. What can conservation strategies learn from the ecosystem services approach?
  3. Implications of Material Flow Cost Accounting for Life Cycle Engineering
  4. Mycorrhiza in tree diversity–ecosystem function relationships
  5. Human–nature connectedness and other relational values are negatively affected by landscape simplification
  6. Dimensionierung von Sicherheitsbeständen
  7. "Glaubt ihr nicht, so bleibt ihr nicht"
  8. One planet
  9. Microstructural pattern formation in finite-deformation single-slip crystal plasticity under cyclic loading
  10. A revised theory of contestable markets
  11. Resources or landmarks
  12. An "intelligent product system" to replace "waste management"
  13. The Values in Crisis Project
  14. §24 Deponiegas
  15. Europe in the classroom: Comenius Projects in Music Education
  16. Disentangling the Pathways and Effects of Ecosystem Service Co-Production
  17. Unterschriftenregelung/Vertretung
  18. Boxsport im schulischen Feld
  19. Industrial relations without conflicts and state interference?
  20. Planting futures
  21. Navigating the Family Support Paradox in Female Entrepreneurship – A Developing Country Perspective
  22. Paid Usership
  23. Special Issue: What do social and environmental responsibilities mean in the ‘Global South’? Towards pluriversal perspectives in management studies
  24. Cybervictimization, self-esteem, and social relationships among German secondary school students
  25. Offshore Oil and LNG Terminals
  26. Der Vorschlag der EU-Kommission für ein EU-Omnibus-Paket zur Änderung von CSRD, CSDDD und Taxonomie-Verordnung