Skip to main content
SpringerLink
Log in

An artificial neural network meta-model for constrained simulation optimization

  • General Paper
  • Published:
Journal of the Operational Research Society

Abstract

This paper presents artificial neural network (ANN) meta-models for expensive continuous simulation optimization (SO) with stochastic constraints. These meta-models are used within a sequential experimental design to approximate the objective function and the stochastic constraints. To capture the non-linear nature of the ANN, the SO problem is iteratively approximated via non-linear programming problems whose (near) optimal solutions obtain estimates of the global optima. Following the optimization step, a cutting plane-relaxation scheme is invoked to drop uninformative estimates of the global optima from the experimental design. This approximation is iterated until a terminating condition is met. To study the robustness and efficiency of the proposed algorithm, a realistic inventory model is used; the results are compared with those of the OptQuest optimization package. These numerical results indicate that the proposed meta-model-based algorithm performs quite competitively while requiring slightly fewer simulation observations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3

Similar content being viewed by others

References

  • Abspoel SJ, Etman LFP, Vervoort J, van Rooij RA, Schoofs AJG and Rooda JE (2001). Simulation based optimization of stochastic systems with integer design variables by sequential multipoint linear approximation. Structural and Multidisciplinary Optimization 22 (2): 125–139.

    Article  Google Scholar 

  • Alkhamis TM and Ahmed MA (2005). Simulation-based optimization for repairable systems using particle swarm algorithm. In: Proceedings of the 2005 Winter Simulation Conference, Orlando, FL, pp 857–861.

  • Altiparmak F, Dengiz B and Bulgak AA (2002). Optimization of buffer sizes in assembly systems using intelligent techniques. In: Proceedings of the 2002 Winter Simulation Conference, San Diego, CA, pp 1157–1162.

  • Banks J and Carson JS (1984). Discrete-Event System Simulation. Prentice-Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Barton RR and Meckesheimer M (2006). Metamodel-based simulation optimization. In: SG Henderson and BL Nelson (eds). Handbooks in Operations Research and Management Science. Elsevier: North Holland, pp 535–574.

    Google Scholar 

  • Bashyam S and Fu MC (1998). Optimization of (s, S) inventory systems with random lead times and a service level constraint. Management Science 44 (12-Part-2): 243–256.

    Article  Google Scholar 

  • Bazaraa MS, Sherali HD and Shetty CM (2006). Nonlinear Programming: Theory and Algorithms. John Wiley and Sons: New Jersey.

    Book  Google Scholar 

  • Biles WE, Kleijnen JPC, van Beers WCM and van Nieuwenhuyse I (2007). Kriging metamodeling in constrained simulation optimization: an explorative study. In: Proceedings of 2007 Winter Simulation Conference, Washington DC, pp 355–362.

  • Can B and Heavey C (2012). A comparison of genetic programming and artificial neural networks in metamodeling of discrete-event simulation models. Computers & Operations Research 39 (2): 424–436.

    Article  Google Scholar 

  • Chang KH, Hong LJ and Wan H (2007). Stochastic trust region gradient-free method (STRONG): A new response-surface-based algorithm in simulation optimization. In: Proceedings of the 2007 Winter Simulation Conference, Washington DC, pp 346–354.

  • Dengiz B, Alabas-Uslu C and Dengiz O (2008). Optimization of manufacturing systems using a neural network metamodel with a new training approach. Journal of the Operational Research Society 60 (9): 1191–1197.

    Article  Google Scholar 

  • Fausett LV (1994). Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Prentice-Hall: Englewood Cliffs, NJ.

    Google Scholar 

  • Fu MC (2006). Gradient estimation. In SG Henderson and BL Nelson (eds). Handbooks in Operations Research and Management Science. Elsevier: North Holland, pp 575–616.

    Google Scholar 

  • Hornik K (1991). Approximation capabilities of multilayer feedforward networks. Neural Networks 4 (2): 251–257.

    Article  Google Scholar 

  • Hurrion RD (1997). An example of simulation optimisation using a neural network metamodel: Finding the optimum number of kanbans in a manufacturing system. Journal of the Operational Research Society 48 (11): 1105–1112.

    Article  Google Scholar 

  • Keys AC and Rees LP (2004). A sequential-design metamodeling strategy for simulation optimization. Computers & Operations Research 31 (11): 1911–1932.

    Article  Google Scholar 

  • Kleijnen JPC (2007). Design and Analysis of Simulation Experiments. Springer: New York.

    Google Scholar 

  • Kleijnen JPC (2008). Response surface methodology for constrained simulation optimization: An overview. Simulation Modelling Practice and Theory 16 (1): 50–64.

    Article  Google Scholar 

  • Kleijnen JPC and Wan J (2007). Optimization of simulated systems: OptQuest and alternatives. Simulation Modelling Practice and Theory 15 (3): 354–362.

    Article  Google Scholar 

  • Kleijnen JPC, van Beers W and van Nieuwenhuyse I (2010). Constrained optimization in expensive simulation: Novel approach. European Journal of Operational Research 202 (1): 164–174.

    Article  Google Scholar 

  • Kwok TY and Yeung DY (1997). Objective functions for training new hidden units in constructive neural networks. Neural Networks, IEEE Transactions on 8 (5): 1131–1148.

    Article  Google Scholar 

  • Law AM (2007). Simulation Modeling and Analysis. 4th edn, McGraw-Hill: Boston, MA.

    Google Scholar 

  • Li YF, Ng SH, Xie M and Goh TN (2010). A systematic comparison of metamodeling techniques for simulation optimization in decision support systems. Applied Soft Computing 10 (4): 1257–1273.

    Article  Google Scholar 

  • Shen C, Wang L and Li Q (2007). Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method. Journal of Materials Processing Technology 183 (2): 412–418.

    Article  Google Scholar 

  • Vosniakos GC, Teifakis A and Benardos P (2006). Neural network simulation metamodels and genetic algorithms in analysis and design of manufacturing cells. The International Journal of Advanced Manufacturing Technology 29 (5-6): 541–550.

    Article  Google Scholar 

  • Wang L (2005). A hybrid genetic algorithm–neural network strategy for simulation optimization. Applied Mathematics and Computation 170 (2): 1329–1343.

    Article  Google Scholar 

  • Yuan R and Guangchen B (2009). Comparison of neural network and Kriging method for creating simulation-optimization metamodels. In: Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing, Chengdu, China, pp 815–821.

Download references

Author information

Authors and Affiliations

  1. Sharif University of Technology, Tehran, Iran

    Ali Mohammad Nezhad & Hashem Mahlooji

Authors
  1. Ali Mohammad Nezhad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hashem Mahlooji
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mohammad Nezhad, A., Mahlooji, H. An artificial neural network meta-model for constrained simulation optimization. J Oper Res Soc 65, 1232–1244 (2014). https://doi.org/10.1057/jors.2013.73

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1057/jors.2013.73

Keywords

Search

Navigation