An interactive multiple-response simulation optimization method

This study proposes a new interactive multicriteria method for determining the best levels of the decision variables needed to optimize a stochastic computer simulation with multiple response variables. The method, called the Pairwise Comparison Stochastic Cutting Plane (PCSCP) method, combines good features from interactive multiple objective mathematical programming and response surface methodology. The major characteristics of the PCSCP method are: (1) it interacts progressively with the decision-maker (DM) to obtain her preferences, (2) it uses experimental design to explore the decision space adequately while reducing the burden on the DM, and (3) it uses the preference information provided by the DM and the sampling error in the responses to reduce the decision space. The mechanics of the method are illustrated with a numerical example. Some computational studies evaluating the method are also reported.

[1]  Gary L. Hogg,et al.  Combining simulation and optimization to solve the multimachine interference problem , 1981 .

[2]  M. Hossein Safizadeh,et al.  Optimization in simulation: Current issues and the future outlook , 1990 .

[3]  S. Jacobson,et al.  Techniques for simulation response optimization , 1989 .

[4]  Dennis E. Smith.  An Empirical Investigation of Optimum-Seeking in the Computer Simulation Situation , 1973, Oper. Res..

[5]  Behnam Malakooti.  Theories and an exact interactive paired-comparison approach for discrete multiple-criteria problems , 1989, IEEE Trans. Syst. Man Cybern..

[6]  William Farrell,et al.  Literature Review and Bibliography of Simulation Optimization , 1977 .

[7]  Gerald W. Evans,et al.  An approach for optimizing multiresponse simulation models , 1991 .

[8]  Wan Seon Shin,et al.  Interactive multiple objective optimization: Survey I - continuous case , 1991, Comput. Oper. Res..

[9]  Marc S. Meketon,et al.  Optimization in simulation: a survey of recent results , 1987, WSC '87.

[10]  Joseph J. Talavage,et al.  A Tradeoff Cut Approach to Multiple Objective Optimization , 1980, Oper. Res..

[11]  James R. Wilson.  Future directions in response surface methodology for simulation , 1987, WSC '87.

[12]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .

[13]  Loren Paul Rees,et al.  Solving Multiple Response Simulation Models Using Modified Response Surface Methodology Within A Lexicographic Goal Programming Framework , 1985 .

[14]  Jeffrey L. Ringuest,et al.  Interactive multiobjective complex search , 1985 .

[15]  M. Deaton,et al.  Response Surfaces: Designs and Analyses , 1989 .

[16]  Farhad Azadivar,et al.  A methodology for solvng multi-objective simulation-optimization problems , 1994 .

[17]  Loren Paul Rees,et al.  SEPARATING THE ART AND SCIENCE OF SIMULATION OPTIMIZATION: A KNOWLEDGE-BASED ARCHITECTURE PROVIDING FOR MACHINE LEARNING , 1993 .

[18]  James J. Swain,et al.  Mathematical programming and the optimization of computer simulations , 1979 .

[19]  Douglas C. Montgomery,et al.  Multiple response surface methods in computer simulation , 1977 .