Dispatching rule selection with Gaussian processes

  • Jens HegerEmail author
  • Torsten Hildebrandt
  • Bernd Scholz-Reiter
Original Paper


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.


Planning and scheduling Dispatching rules Machine learning Gaussian processes Production management and logistics 



The authors are grateful to the generous support by the German Research Foundation (DFG) under grant SCHO 540/17-2.


  1. Alpaydin E (2004) Introduction to machine learning (adaptive computation and machine learning series), vol 14. The MIT Press, CambridgeGoogle Scholar
  2. Becker T, Windt K (2011) A comparative view on existing autonomous control approaches: observations from a simulation study. In: Hülsmann M, Scholz-Reiter B, Windt K (eds) Autonomous cooperation and control in logistics. Springer Berlin Heidelberg, pp 275–289Google Scholar
  3. Blackstone JH, Phillips DT, Hogg GL (1982) A state-of-the-art survey of dispatching rules for manufacturing job shop operations. Int J Prod Res 20(1):27–45CrossRefGoogle Scholar
  4. Conway RW (1965) Priority dispatching and job lateness in a job shop. J Ind Eng 16:228–237Google Scholar
  5. Dashkovskiy S, Karimi HR, Kosmykov M (2012) A Lyapunov-Razumikhin approach for stability analysis of logistics networks with time-delays. Int J Syst Sci 43(5):845–853CrossRefGoogle Scholar
  6. El-Bouri A, Shah P (2006) A neural network for dispatching rule selection in a job shop. Int J Adv Manuf Technol 31(3–4):342–349CrossRefGoogle Scholar
  7. Guneri AF, Gumus AT (2008) Artificial neural networks for finite capacity scheduling: a comparative study. Int J Ind Eng 15(4):349–359Google Scholar
  8. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten H (2009) The weka data mining software: an update. SIGKDD Explor Newsl 11(1):10–18CrossRefGoogle Scholar
  9. Hvalica D (2012) Solving job shop problems in the context of hypergraphs. Central Eur J Oper Res 21(1): 1–14. doi: 10.1007/s10100-012-0268-1
  10. Haupt R (1989) A survey of priority rule-based scheduling. Oper Res Spektrum 11(1):3–16CrossRefGoogle Scholar
  11. Heger J, Hildebrandt T, Scholz-Reiter B (2013) Switching dispatching rules with Gaussian processes. In: Windt K (ed) Lecture notes in production engineering: Robust manufacturing control. Springer, BerlinGoogle Scholar
  12. Hentsch K, Köchel P (2011) Job scheduling with forbidden setups and two objectives using genetic algorithms and penalties. Central Eur J Oper Res 19:285–298CrossRefGoogle Scholar
  13. Hildebrandt T, Heger J, Scholz-Reiter B (2010) Towards improved dispatching rules for complex shop floor scenarios: a genetic programming approach. In: Proceedings of the 12th annual conference on genetic and evolutionary computation, Portland, USA, pp 257–264Google Scholar
  14. Holthaus O, Rajendran C (1997) Efficient dispatching rules for scheduling in a job shop. Int J Prod Econ 48(1):87–105CrossRefGoogle Scholar
  15. Holthaus O, Rajendran C (2000) Efficient jobshop dispatching rules: further developments. Prod Plan Control 11(2):171–178CrossRefGoogle Scholar
  16. Huffman BJ (2001) An object-oriented version of SIMLIB (a simple simulation package). INFORMS Trans Educ 2(1):1–15CrossRefGoogle Scholar
  17. Karimi HR, Duffie NA, Dashkovskiy S (2010) Local capacity H\_infinity control for production networks of autonomous work systems with time-varying delays. IEEE Trans Autom Sci Eng 7(4):849–857CrossRefGoogle Scholar
  18. Kotsiantis SB (2007) Supervised machine learning: a review of classification techniques. Informatica 31:249–268Google Scholar
  19. Law AM (2007) Simulation modeling and analysis, 4th edn. McGraw-Hill, BostonGoogle Scholar
  20. MacKay DJC (1998) Introduction to Gaussian processes. In: Bishop CM (ed) Neural networks and machine learning, NATO ASI series, vol 168. Springer, Berlin, pp 133–165Google Scholar
  21. Mouelhi-Chibani W, Pierreval H (2010) Training a neural network to select dispatching rules in real time. Comput Ind Eng 58(2):249–256. Scheduling in Healthcare and Industrial SystemsGoogle Scholar
  22. Neal RM (1996) Bayesian learning for neural networks (Lecture Notes in Statistics), 1st edn. Springer, BerlinGoogle Scholar
  23. O’Hagan A (1978) Curve fitting and optimal design. J R Stat Soc 40(1):1–42Google Scholar
  24. Paciorek CJ, Schervish MJ (2004) Nonstationary covariance functions for gaussian process regression. In: Proceedings of the conference on neural information processing systems (NIPS). MIT PressGoogle Scholar
  25. Panwalkar SS, Iskander W (1977) A survey of scheduling rules. Oper Res 25(1):45–61CrossRefGoogle Scholar
  26. Plagemann C, Kersting K, Burgard W (2008) Nonstationary Gaussian process regression using point estimates of local smoothness. In: Daelemans W, Goethals B, Morik K (eds) Machine learning and knowledge discovery in databases, vol 5212. Springer Berlin Heidelberg, pp 204–219Google Scholar
  27. Priore P, de la Fuente D, Gomez A, Puente J (2001) A review of machine learning in dynamic scheduling of flexible manufacturing systems. AI EDAM 15(03):251–263Google Scholar
  28. Rajendran C, Holthaus O (1999) A comparative study of dispatching rules in dynamic flowshops and jobshops. Eur J Oper Res 116(1):156–170CrossRefGoogle Scholar
  29. Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning (adaptive computation and machine learning). The MIT Press, CambridgeGoogle Scholar
  30. Rasmussen CE (1996) Evaluation of Gaussian processes and other methods for non-linear regression. PhD thesis, Department of Computer Science, University of TorontoGoogle Scholar
  31. Sun YL, Yih Y (1996) An intelligent controller for manufacturing cells. Int J Prod Res 34(8):2353–2373CrossRefGoogle Scholar
  32. Wilbrecht JK, Prescott WB (1969) The influence of setup time on job shop performance. Manag Sci 16(4):274–280CrossRefGoogle Scholar
  33. Williams C (2006) Gaussian processes for machine learning—software examples.
  34. Williams CKI, Rasmussen CE (1996) Gaussian processes for regression. Adv Neural Inf Process Syst 8:514–520Google Scholar
  35. Wu S-YD, Wysk RA (1989) An application of discrete-event simulation to on-line control and scheduling in flexible manufacturing. Int J Prod Res 27(9):1603–1623CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jens Heger
    • 1
    Email author
  • Torsten Hildebrandt
    • 1
  • Bernd Scholz-Reiter
    • 1
  1. 1.BIBA, Bremer Institut für Produktion und Logistik GmbHUniversity of BremenBremenGermany

Personalised recommendations