Modified SBX and adaptive mutation for real world single objective optimization

Real-world optimization problems often involve highly non-linear objectives and constraints. From an application point of view, it is usually desirable that the global optimum be achieved in such cases. Among selection, crossover and mutation operators of a genetic algorithm, the last two are responsible for search and diversity maintenance. By improving these operators, the efficiency of GAs can be improved. In this paper, we solve the problems specified in “CEC 2011 Competition on Testing Evolution Algorithms on Real World Optimization Problems” using a variation of the Simulated Binary Crossover (SBX) which adaptively shifts between parent-centric and mean-centric recombinations. The shift occurs automatically during program execution through the use of current population statistics and is expected to improve the performance of GA. Further, we also employ a self-adaptive mutation strategy developed earlier.

[1]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[2]  Aimo A. Törn,et al.  Global Optimization , 1999, Science.

[3]  P. N. Suganthan,et al.  Problem Definitions and Evaluation Criteria for CEC 2011 Competition on Testing Evolutionary Algorithms on Real World Optimization Problems , 2011 .

[4]  Heinz Mühlenbein,et al.  Fuzzy Recombination for the Breeder Genetic Algorithm , 1995, ICGA.

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[8]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[9]  Francisco Herrera,et al.  Tackling Real-Coded Genetic Algorithms: Operators and Tools for Behavioural Analysis , 1998, Artificial Intelligence Review.

[10]  J. D. Schaffer,et al.  Some experiments in machine learning using vector evaluated genetic algorithms (artificial intelligence, optimization, adaptation, pattern recognition) , 1984 .

[11]  Thomas Bäck,et al.  Evolutionary computation: Toward a new philosophy of machine intelligence , 1997, Complex..

[12]  KalyanmoyDebandSamirAgrawal KanpurGeneticAlgorithmsLaboratory,et al.  A Niched-Penalty Approach for Constraint Handling in Genetic Algorithms , 2002 .

[13]  Kalyanmoy Deb,et al.  Hybrid gradient projection based Genetic Algorithms for constrained optimization , 2010, IEEE Congress on Evolutionary Computation.

[14]  Kalyanmoy Deb,et al.  Self-Adaptive Parent to Mean-Centric Recombination for Real-Parameter Optimization , 2011 .

[15]  Kalyanmoy Deb,et al.  Simulated Binary Crossover for Continuous Search Space , 1995, Complex Syst..

[16]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[17]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .