A Parameter Tuning Methodology for Metaheuristics Based on Design of Experiments

Many parameters have to be tuned for any metaheuristics. Parameter tuning may permit a superior flexibility and robustness , but requires a careful initialization. Those parameters may have a large influence on the efficiency and effectiveness of the search. The optimal values for the parameters m ainly depend on the problem. In order to let a project to be replicated, a standard procedure as a methodology is required. In this paper, a parameter tuning methodology for metaheuristics based on design of experiments is proposed. The proposed methodolog y comprises five phases, namely, Problem Characteristics Screening, Clustering, Parameter Screening, Response Surface Modeling and Optimization. The proposed methodology is applied to the Ant Colony System algorithm for solving 47 traveling salesman problem instances. For validation of the proposed methodology, the different alternative approaches for parameter tuning are compared and it is concluded that, the methodology presents better results than the other alternative approaches.

[1]  Ashwin Srinivasan,et al.  Parameter Screening and Optimisation for ILP using Designed Experiments , 2011, J. Mach. Learn. Res..

[2]  Mauro Birattari.  The Problem of Tuning Metaheuristics , 2005 .

[3]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[4]  Frank Hutter,et al.  Automated configuration of algorithms for solving hard computational problems , 2009 .

[5]  Mauro Birattari,et al.  Tuning Metaheuristics - A Machine Learning Perspective , 2009, Studies in Computational Intelligence.

[6]  Yeong-Dae Kim,et al.  A systematic procedure for setting parameters in simulated annealing algorithms , 1998, Comput. Oper. Res..

[7]  Alex Van Breedam,et al.  Improvement heuristics for the Vehicle Routing Problem based on simulated annealing , 1995 .

[8]  Mark E. Johnson,et al.  A case study in experimental design applied to genetic algorithms with applications to DNA sequence assembly , 1997 .

[9]  Marco Caserta,et al.  A cross entropy-Lagrangean hybrid algorithm for the multi-item capacitated lot-sizing problem with setup times , 2009, Comput. Oper. Res..

[10]  El-Ghazali Talbi,et al.  Metaheuristics - From Design to Implementation , 2009 .

[11]  Thomas Stützle,et al.  Improvement Strategies for the F-Race Algorithm: Sampling Design and Iterative Refinement , 2007, Hybrid Metaheuristics.

[12]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[13]  George C. Runger,et al.  Using Experimental Design to Find Effective Parameter Settings for Heuristics , 2001, J. Heuristics.

[14]  S. D. Hutagalung,et al.  Optimisation of nanooxide mask fabricated by atomic force microscopy nanolithography: A response surface methodology application , 2012 .

[15]  F. Ahmadun,et al.  Optimization of carbon nano tubes synthesis using fluidized bed chemical vapor deposition: A statistical approach , 2013 .

[16]  Daniel Kudenko,et al.  Tuning an Algorithm Using Design of Experiments , 2010, Experimental Methods for the Analysis of Optimization Algorithms.

[17]  F. Hutter,et al.  ParamILS: an automatic algorithm configuration framework , 2009 .

[18]  Orhan Engin,et al.  Investigation of Ant System parameter interactions by using design of experiments for job-shop scheduling problems , 2009, Comput. Ind. Eng..

[19]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[20]  Manuel Laguna,et al.  Fine-Tuning of Algorithms Using Fractional Experimental Designs and Local Search , 2006, Oper. Res..

[21]  Daniel Kudenko,et al.  Tuning the Performance of the MMAS Heuristic , 2007, SLS.

[22]  Daniel Kudenko,et al.  Determining Whether a Problem Characteristic Affects Heuristic Performance , 2008, Recent Advances in Evolutionary Computation for Combinatorial Optimization.