Gaussian processes for dispatching rule selection in production scheduling: Comparison of learning techniques

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

Authors

Decentralized scheduling with dispatching rules is applied in many fields of logistics and production, especially in semiconductor manufacturing, which is characterized by high complexity and dynamics. Many dispatching rules have been found, which perform well on different scenarios, however no rule has been found, which outperforms other rules across various objectives. To tackle this drawback, approaches, which select dispatching rules depending on the current system conditions, have been proposed. Most of these use learning techniques to switch between rules regarding the current system status. Since the study of Rasmussen [1] has shown that Gaussian processes as a machine learning technique have outperformed other techniques like neural networks under certain conditions, we propose to use them for the selection of dispatching rules in dynamic scenarios. Our analysis has shown that Gaussian processes perform very well in this field of application. Additionally, we showed that the prediction quality Gaussian processes provide could be used successfully. © 2010 IEEE.
Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
Number of pages8
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date2010
Pages631-638
ISBN (print)978-1-4244-9244-2
ISBN (electronic)978-0-7695-4257-7
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event10th IEEE International Conference on Data Mining Workshops - 2010 - Sydney, Australia
Duration: 14.12.201017.12.2010
Conference number: 10
http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=7127

DOI

Recently viewed

Publications

  1. Kalman Filter for Predictive Maintenance and Anomaly Detection
  2. Aspect-oriented software development
  3. Article 11: Formal validity
  4. Modernizing persistence–bioaccumulation–toxicity (PBT) assessment with high throughput animal-free methods
  5. Improvements and future challenges for the research infrastructure in the field firm level data
  6. Oddih
  7. Navigating in the Digital Jungle: Articulating Combinatory Affordances of Digital Infrastructures for Collaboration
  8. Analyzing the Influence of Knowledge Graph Information on Relation Extraction
  9. Towards greener and sustainable ionic liquids using naturally occurring and nature-inspired pyridinium structures
  10. I can make it!
  11. Integration of demand forecasts in ABC-XYZ analysis
  12. Material system analysis
  13. Audio-Hacks
  14. Intra-specific leaf trait responses to species richness at two different local scales
  15. A sensitive microsystem as biosensor for cell growth monitoring and antibiotic testing
  16. Multimodal analysis of spatially heterogeneous microstructural refinement and softening mechanisms in three-pass friction stir processed Al-4Si alloy
  17. Let’s Team Up with AI! Toward a Hybrid Intelligence System for Online Customer Service
  18. Atlas
  19. Valuing Ecosystem Services in Terms of Ecological Risks and Returns
  20. On the way to greener ionic liquids
  21. Kontrolle, Ritus, Simulation
  22. Applying the HES-framework
  23. On the Epistemology of Computer Simulation
  24. Der Kunstraum
  25. Mythos
  26. Daniel Fiott (ed.), The csdp in 2020: The EU’s legacy and ambition in security and defence