Classifying Metamodeling Methods for Evolutionary Multi-objective Optimization: First Results

In many practical optimization problems, evaluation of objectives and constraints often involve computationally expensive procedures. To handle such problems, a metamodel-assisted approach is usually used to complete an optimization run in a reasonable amount of time. A metamodel is an approximate mathematical model of an objective or a constrained function which is constructed with a handful of solutions evaluated exactly. However, when comes to solving multi-objective optimization problems involving numerous constraints, it may be too much to metamodel each and every objective and constrained function independently. The cumulative effect of errors from each metamodel may turn out to be detrimental for the accuracy of the overall optimization procedure. In this paper, we propose a taxonomy of various metamodeling methodologies for multi-objective optimization and provide a comparative study by discussing advantages and disadvantages of each method. The first results presented in this paper are obtained using the well-known Kriging metamodeling approach. Based on our proposed taxonomy and an extensive literature search, we also highlight new and promising methods for multi-objective metamodeling algorithms.

[1]  Bithin Datta,et al.  Multi-objective management of saltwater intrusion in coastal aquifers using genetic programming and modular neural network based surrogate models. , 2010 .

[2]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[3]  Liborio Cavaleri,et al.  Prediction of the Fundamental Period of Infilled RC Frame Structures Using Artificial Neural Networks , 2015, Comput. Intell. Neurosci..

[4]  Kalyanmoy Deb,et al.  A fast and accurate solution of constrained optimization problems using a hybrid bi-objective and penalty function approach , 2010, IEEE Congress on Evolutionary Computation.

[5]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[6]  K. Deb.  An Efficient Constraint Handling Method for Genetic Algorithms , 2000 .

[7]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..

[8]  Bernhard Sendhoff,et al.  Multi co-objective evolutionary optimization: Cross surrogate augmentation for computationally expensive problems , 2012, 2012 IEEE Congress on Evolutionary Computation.

[9]  Kalyanmoy Deb,et al.  An Optimality Theory-Based Proximity Measure for Set-Based Multiobjective Optimization , 2016, IEEE Transactions on Evolutionary Computation.

[10]  John E. Dennis,et al.  Normal-Boundary Intersection: A New Method for Generating the Pareto Surface in Nonlinear Multicriteria Optimization Problems , 1998, SIAM J. Optim..

[11]  Kalyanmoy Deb,et al.  An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints , 2014, IEEE Transactions on Evolutionary Computation.

[12]  Yu Zhang,et al.  Multi-objective optimization of double suction centrifugal pump using Kriging metamodels , 2014, Adv. Eng. Softw..

[13]  Shigeru Obayashi,et al.  Kriging Surrogate Model Enhanced by Coordinate Transformation of Design Space Based on Eigenvalue Decomposition , 2015, EMO.

[14]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[15]  Kalyanmoy Deb,et al.  A Generative Kriging Surrogate Model for Constrained and Unconstrained Multi-objective Optimization , 2016, GECCO.

[16]  R. S. Laundy,et al.  Multiple Criteria Optimisation: Theory, Computation and Application , 1989 .

[17]  Hendrik Blockeel,et al.  Multi-objective optimization with surrogate trees , 2013, GECCO '13.

[18]  David Herrero Pérez,et al.  Kriging-based infill sampling criterion for constraint handling in multi-objective optimization , 2016, J. Glob. Optim..

[19]  Saúl Zapotecas Martínez,et al.  MOEA/D assisted by rbf networks for expensive multi-objective optimization problems , 2013, GECCO '13.

[20]  Fabio Schoen,et al.  Global optimization of expensive black box problems with a known lower bound , 2013, J. Glob. Optim..

[21]  Christos Makropoulos,et al.  Multiobjective optimisation on a budget: Exploring surrogate modelling for robust multi-reservoir rules generation under hydrological uncertainty , 2015, Environ. Model. Softw..

[22]  Joshua D. Knowles,et al.  ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems , 2006, IEEE Transactions on Evolutionary Computation.

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

[24]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[25]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[26]  Carlos A. Coello Coello,et al.  A Review of Techniques for Handling Expensive Functions in Evolutionary Multi-Objective Optimization , 2010 .

[27]  Bernd Bischl,et al.  Model-Based Multi-objective Optimization: Taxonomy, Multi-Point Proposal, Toolbox and Benchmark , 2015, EMO.

[28]  P. Bouillard,et al.  Hierarchical stochastic metamodels based on moving least squares and polynomial chaos expansion , 2011 .

[29]  Khaled Rasheed,et al.  A Survey of Fitness Approximation Methods Applied in Evolutionary Algorithms , 2010 .

[30]  Edgar Tello-Leal,et al.  A Review of Surrogate Assisted Multiobjective Evolutionary Algorithms , 2016, Comput. Intell. Neurosci..