Efficient global optimisation for black-box simulation via sequential intrinsic Kriging

Abstract Efficient global optimisation (EGO) is a popular method that searches sequentially for the global optimum of a simulated system. EGO treats the simulation model as a black-box, and balances local and global searches. In deterministic simulation, classic EGO uses ordinary Kriging (OK), which is a special case of universal Kriging (UK). In our EGO variant we use intrinsic Kriging (IK), which does not need to estimate the parameters that quantify the trend in UK. In random simulation, classic EGO uses stochastic Kriging (SK), but we replace SK by stochastic IK (SIK). Moreover, in random simulation, EGO needs to select the number of replications per simulated input combination, accounting for the heteroscedastic variances of the simulation outputs. A popular method uses optimal computer budget allocation (OCBA), which allocates the available total number of replications to simulated combinations. We replace OCBA by a new allocation algorithm. We perform several numerical experiments with deterministic simulations and random simulations. These experiments suggest that (1) in deterministic simulations, EGO with IK outperforms classic EGO; (2) in random simulations, EGO with SIK and our allocation rule does not perform significantly better than EGO with SK and OCBA.

[1]  N. Zheng,et al.  Global Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models , 2006, J. Glob. Optim..

[2]  Robert Haining,et al.  Statistics for spatial data: by Noel Cressie, 1991, John Wiley & Sons, New York, 900 p., ISBN 0-471-84336-9, US $89.95 , 1993 .

[3]  Lihua Sun,et al.  Balancing Exploitation and Exploration in Discrete Optimization via Simulation Through a Gaussian Process-Based Search , 2014, Oper. Res..

[4]  Yves Deville,et al.  DiceKriging, DiceOptim: Two R Packages for the Analysis of Computer Experiments by Kriging-Based Metamodeling and Optimization , 2012 .

[5]  Barry L. Nelson,et al.  Discrete optimization via simulation using Gaussian Markov random fields , 2014, Proceedings of the Winter Simulation Conference 2014.

[6]  Barry L. Nelson,et al.  Stochastic kriging for simulation metamodeling , 2008, 2008 Winter Simulation Conference.

[7]  Jack P. C. Kleijnen,et al.  Classic Kriging versus Kriging with bootstrapping or conditional simulation: classic Kriging’s robust confidence intervals and optimization , 2014, J. Oper. Res. Soc..

[8]  Victor Picheny,et al.  Quantile-Based Optimization of Noisy Computer Experiments With Tunable Precision , 2013, Technometrics.

[9]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[10]  Ruth Davies,et al.  Automated selection of the number of replications for a discrete-event simulation , 2010, J. Oper. Res. Soc..

[11]  Chun-Hung Chen,et al.  Simulation Budget Allocation for Further Enhancing the Efficiency of Ordinal Optimization , 2000, Discret. Event Dyn. Syst..

[12]  Jack P. C. Kleijnen,et al.  Stochastic Intrinsic Kriging for Simulation Metamodelling , 2015 .

[13]  Loo Hay Lee,et al.  Simulation optimization via kriging: a sequential search using expected improvement with computing budget constraints , 2013 .

[14]  Frances A. O'Brien,et al.  The use of search experimentation in discrete-event simulation practice , 2015, J. Oper. Res. Soc..

[15]  Ehsan Mehdad,et al.  Kriging metamodels and global opimization in simulation , 2015 .

[16]  J. Chilès,et al.  Geostatistics: Modeling Spatial Uncertainty , 1999 .

[17]  Robert E. Shannon,et al.  Design and analysis of simulation experiments , 1978, WSC '78.

[18]  Alan J. Mayne,et al.  Towards Global Optimisation 2 , 1976 .

[19]  Robert B. Gramacy,et al.  Cases for the nugget in modeling computer experiments , 2010, Statistics and Computing.

[20]  J. Yin,et al.  Kriging metamodel with modified nugget-effect: The heteroscedastic variance case , 2011, Comput. Ind. Eng..

[21]  Jerome Sacks,et al.  Choosing the Sample Size of a Computer Experiment: A Practical Guide , 2009, Technometrics.

[22]  David Ginsbourger,et al.  Multiples métamodèles pour l'approximation et l'optimisation de fonctions numériques multivariables , 2009 .

[23]  M. Wand,et al.  Kriging with Nonparametric Variance Function Estimation , 1999, Biometrics.