Using a Goal-Switching Selection Operator in Multi-Objective Genetic Algorithm Optimization Problems

This paper demonstrates how solution quality for multiobjective optimization problems can be improved by altering the selection phase of a multiobjective genetic algorithm. Rather than the traditional roulette selection used in algorithms like NSGA-II, this paper adds a goal switching technique to the selection operator. Goal switching in this context represents the rotation of the selection operator among a problem’s various objective functions to increase search diversity. This rotation can be specified over a set period of generations, evaluations, CPU time, or other factors defined by the designer. This technique is tested using a set period of generations before switching occurs, with only one objective considered at a time. Two test cases are explored, the first as identified in the Congress on Evolutionary Computation (CEC) 2009 special session and the second a case study concerning the market-driven design of a MP3 player product line. These problems were chosen because the first test case’s Pareto frontier is continuous and concave while being relatively easy to find. The second Pareto frontier is more difficult to obtain and the problem’s design space is significantly more complex. Selection operators of roulette and roulette with goal switching were tested with 3 to 7 design variables for the CEC 09 problem, and 81 design variables for the MP3 player problem. Results show that goal switching improves the number of Pareto frontier points found and can also lead to improvements in hypervolume and/or mean time to convergence.Copyright © 2013 by ASME

[1]  J. Dennis,et al.  A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems , 1997 .

[2]  Eliot Winer,et al.  Visual design steering for optimization solution improvement , 2000 .

[3]  Cláudio F. Lima,et al.  Adaptive Population Sizing Schemes in Genetic Algorithms , 2007, Parameter Setting in Evolutionary Algorithms.

[4]  Shengxiang Yang,et al.  A Comparative Study of Adaptive Mutation Operators for Genetic Algorithms , 2009 .

[5]  Kemper Lewis,et al.  Intuitive visualization of Pareto Frontier for multi-objective optimization in n-dimensional performance space , 2004 .

[6]  Zbigniew Michalewicz,et al.  Parameter control in evolutionary algorithms , 1999, IEEE Trans. Evol. Comput..

[7]  Zbigniew Michalewicz,et al.  Parameter Control in Evolutionary Algorithms , 2007, Parameter Setting in Evolutionary Algorithms.

[8]  Qingfu Zhang,et al.  Multiobjective optimization Test Instances for the CEC 2009 Special Session and Competition , 2009 .

[9]  Jonathan E. Fieldsend,et al.  A MOPSO Algorithm Based Exclusively on Pareto Dominance Concepts , 2005, EMO.

[10]  Carlos A. Coello Coello,et al.  A Micro-Genetic Algorithm for Multiobjective Optimization , 2001, EMO.

[11]  William M. Spears,et al.  A Study of Crossover Operators in Genetic Programming , 1991, ISMIS.

[12]  Timothy W. Simpson,et al.  Visual Steering Commands for Trade Space Exploration: User-Guided Sampling With Example , 2009, J. Comput. Inf. Sci. Eng..

[13]  Jay D. Martin,et al.  The ARL Trade Space Visualizer: An Engineering Decision-Making Tool , 2004 .

[14]  Alden H. Wright,et al.  Periodical switching between related goals for improving evolvability to a fixed goal in multi-objective problems , 2009, Inf. Sci..

[15]  Patrick M. Reed,et al.  Diagnostic assessment of the borg MOEA for many-objective product family design problems , 2012, 2012 IEEE Congress on Evolutionary Computation.

[16]  L. Ding,et al.  Various selection approaches on evolutionary multiobjective optimization , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

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

[18]  Scott Ferguson,et al.  Creating targeted initial populations for genetic product searches in heterogeneous markets , 2014 .

[19]  Jeffrey Horn,et al.  The Niched Pareto Genetic Algorithm 2 Applied to the Design of Groundwater Remediation Systems , 2001, EMO.

[20]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[21]  Eliot Winer,et al.  Visual design steering for optimization solution improvement , 2001 .

[22]  John M. Wilson,et al.  Comparing efficiencies of genetic crossover operators for one machine total weighted tardiness problem , 2008, Appl. Math. Comput..

[23]  Shapour Azarm,et al.  Metrics for Quality Assessment of a Multiobjective Design Optimization Solution Set , 2001 .

[24]  Chandrabose Aravindan,et al.  Design of Hybrid Genetic Algorithm with Preferential Local Search for Multiobjective Optimization Problems , 2011 .

[25]  Xavier Blasco Ferragud,et al.  A new graphical visualization of n-dimensional Pareto front for decision-making in multiobjective optimization , 2008, Inf. Sci..

[26]  Imtiaz Ali Korejo,et al.  Adaptive mutation operators for evolutionary algorithms , 2012 .

[27]  Kemper Lewis,et al.  Multi-Attribute Decision Making Using Hypothetical Equivalents and Inequivalents , 2004 .

[28]  Peter J. Angeline,et al.  Adaptive and Self-adaptive Evolutionary Computations , 1995 .

[29]  Kaisa Miettinen,et al.  On initial populations of a genetic algorithm for continuous optimization problems , 2007, J. Glob. Optim..

[30]  Yilmaz Kaya,et al.  A Novel Crossover Operator for Genetic Algorithms: Ring Crossover , 2011, ArXiv.

[31]  S. Utyuzhnikov,et al.  Directed search domain: a method for even generation of the Pareto frontier in multiobjective optimization , 2011 .

[32]  Varghese S. Jacob,et al.  An investigation of mating and population maintenance strategies in hybrid genetic heuristics for product line designs , 2006, Comput. Oper. Res..

[33]  Patrick M. Reed,et al.  Borg: An Auto-Adaptive Many-Objective Evolutionary Computing Framework , 2013, Evolutionary Computation.

[34]  Mustafa Kaya,et al.  The effects of a new selection operator on the performance of a genetic algorithm , 2011, Appl. Math. Comput..

[35]  Huowang Chen,et al.  The multi-criteria minimum spanning tree problem based genetic algorithm , 2007, Inf. Sci..

[36]  S. Rajeev,et al.  Discrete Optimization of Structures Using Genetic Algorithms , 1992 .

[37]  Pedro A. Diaz-Gomez,et al.  Initial Population for Genetic Algorithms: A Metric Approach , 2007, GEM.

[38]  Daniel E. Hastings,et al.  Multi-Attribute Tradespace Exploration as Front End for Effective Space System Design , 2004 .

[39]  Cliff T. Ragsdale,et al.  A decision support system for the electrical power districting problem , 2003, Decis. Support Syst..

[40]  J.T. Alander,et al.  On optimal population size of genetic algorithms , 1992, CompEuro 1992 Proceedings Computer Systems and Software Engineering.

[41]  Kemper Lewis,et al.  Hyper-Radial Visualization for Multi-objective Decision-making Support Under Uncertainty Using Preference Ranges: The PRUF Method , 2008 .

[42]  Thomas Bräunl,et al.  Population variation in genetic programming , 2007, Inf. Sci..

[43]  C.A. Coello Coello,et al.  MOPSO: a proposal for multiple objective particle swarm optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[44]  Tung-Kuan Liu,et al.  Improved genetic algorithm for mixed-discrete-continuous design optimization problems , 2010 .

[45]  Mustafa Kaya,et al.  The effects of two new crossover operators on genetic algorithm performance , 2011, Appl. Soft Comput..

[46]  Brian J. German,et al.  Rave: A Computational Framework to Facilitate Research in Design Decision Support , 2012, J. Comput. Inf. Sci. Eng..

[47]  Susana Cecilia Esquivel,et al.  Solving Hard Multiobjective Problems with a Hybridized Method , 2010 .

[48]  Michael N. Vrahatis,et al.  Multi-Objective Particles Swarm Optimization Approaches , 2008 .

[49]  Yusof Rubiyah,et al.  A new mutation operation for faster convergence in genetic algorithm feature selection , 2012 .

[50]  A. Messac,et al.  Aggregate Objective Functions and Pareto Frontiers: Required Relationships and Practical Implications , 2000 .

[51]  Jasbir S. Arora,et al.  Survey of multi-objective optimization methods for engineering , 2004 .

[52]  Garrett Foster,et al.  Expansion of Alternative Generation Techniques. , 2011 .

[53]  Glynn J. Sundararaj,et al.  Ability of Objective Functions to Generate Points on Nonconvex Pareto Frontiers , 2000 .

[54]  Jongsoo Lee,et al.  An implementation of new selection strategies in a genetic algorithm – population recombination and elitist refinement , 2011 .

[55]  A. E. Eiben,et al.  Multiobjective Evolutionary Algorithms , 2015 .