PROBABILISTIC CONSIDERATIONS UNDERLYING A NOVEL EVOLUTIONARY COMPUTATION

Abstract

multiobjective optimization but also for constraint optimization. Although there are several excellent papers on the penalty function approaches, up till now there is no clear method for the systematic selection of penalty parameters per constraint since the topic is quite elusive. The issues being well-realized, there are several researches addressing these issues to some extent. However, still, the robustness of these methods remains the main issue due to some newly added additional parameters subject to determination. This work endeavours to address this issue and first, it makes a systematic analysis. Following the analysis, it establishes a probabilistic approach as the issue is entirely in the domain of probability. According to the best knowledge of the authors, the approach is unique as to probabilistic treatment of the issue. The approach models the probability density of the random population throughout the generations and based on this, penalty parameters are determined following the probabilistic derivations. The theoretical considerations are substantiated by computer experiments and a demonstrative example is presented showing the salient effectiveness of the approach.

Keywords

• Evolutionary algorithm
• multiobjective optimization
• constraint optimization
• probabilistic modeling

References

1. [1] A. Homaifar, S. H. V. Lai, and X. Qi, "Constrained optimization via genetic algorithms," Simulation, vol. 9, p. 19, 1994.
2. [2] Z. Michalewicz and M. Schoenauer, "Evolutuionary algorithms for constrained parameter optimization problems," Evolutionary Computation, vol. 4, p. 33, 1996.
3. [3] Z. Michalewicz, Genetic Algorithms+ Data Structures=Evolution Programs. Berlin: Springer, 1999.
4. [4] S. Venkatraman and G. G. Yen, "A Generic Framework for Constrained Optimization Using Genetic Algorithms," IEEE Trans. Evolutionary Computation, vol. 9, p. 12, 2005.
5. [5] Z. Huang and H. Tian, "A genetic algorithm with constrained sorting method for constrained optimization problems," presented at the IEEE International Conference on Intelligent Computing and Intelligent Systems, 2009. ICIS 2009. , Shanghai 2009.
6. [6] A. C. A. Coello, "Use of a self adaptive penalty approach for engineering optimization problems," Computers in Industry, vol. 41, pp. 113–127, 2000.
7. [7] S. B. Hamida and M. Schoenauer, "An adaptive algorithm for constraint optimization problems," in Lecture Notes on Computer Science PPSN 2000. vol. 1917, K. Deb, Ed., ed Heidelberg: Springer, 2000, pp. 529-538.
8. [8] S. B. Hamida and M. Schoenauer, "ASHEA: New results using adaptive segregtional constraint handling," presented at the IEEE Congress on Evolutionary Computation (CEC 2002), Honolulu, Hawaii, 2002.

9. [9] F. Hoffmeister and J. Sprave, "Problem-independent handling of constraints by use of metric penalty functions," presented at the Fifth Annual conference on evolutionary programming EP 1996, San Diego, CA, 1996.
10. [10] H. Sarimveis and A. Nikolakopoulos, "A line up evolutionary algorithm for solving non-linear constraint optimization problems," Computers & Operations Research vol. 32, pp. 1499-1514, 2005.
11. [11] K. Deb, "An efficient constraint handling method for genetic algorithms.," Computer Methods in Applied Mechanics and Engineering, vol. 186, p. 28, 2000.
12. [12] T. Ray, H. K. Singh, A. Isaacs, and W. Smith, "Infeasibility driven evolutionary algorithm for constrained optimization," in ConstraintHandling in Evolutionary Optimization, ed Berlin: Springer, 2009, pp.145-165.
13. [13] K. Deb and R. Datta, "A fast and accurate solution of constrained optimization problems using a hybrid bi-objective and penalty function approach," presented at the Evolutionary Computation (CEC), 2010 IEEE Congress on, Barcelona 2010.
14. [14] S. Gass and T. Saaty, "The computational algorithm for the parametric objective function," Naval Research Logistics Quarterly, vol. 2, p. 7, 1955.
15. [15] L. Zadeh, "Non-scalar-valued performance criteria," IEEE Trans. Automatic Control, vol. 8, p. 2, 1963.
16. [16] K. Miettinen, Nonlinear Multiobjective Optimization. Boston: Kluwer Academic, 1999.
17. [17] Y. Y. Haimes, L. S. Lasdon, and D. A. Wismer, "On a bicriterion formulation of the problems of integrated system identification and system optimization," IEEE Trans. Systems, Man, and Cybernetics, vol. 1, p. 2, 1971.
18. [18] G. Bachman and L. Narici, Functional Analysis. New York: Dover, 2000.
19. [19] J. T. Oden and L. F. Demkowicz, Applied Functional Analysis: CRC Press, 1996.
20. [20] D. M. Himmelblau, Applied Nonlinear Programming: Mc-Graw-Hill, USA, 1972.