A Reduced-Cost SMS-EMOA Using Kriging, Self-Adaptation, and Parallelization

  • Jan-Willem Klinkenberg
  • Michael T. M. Emmerich
  • André H. Deutz
  • Ofer M. Shir
  • Thomas Bäck
Conference paper
Part of the Lecture Notes in Economics and Mathematical Systems book series (LNE, volume 634)

Abstract

The SMS-EMOA is a simple and powerful evolutionary metaheuristic for computing approximations to Pareto front based on the dominated hypervolume indicator (S-metric). However, as other state-of-the-art metaheuristics, it consumes a high number of function evaluations in order to compute accurate approximations. To reduce its total computational cost and response time for problems with time consuming evaluators, we suggest three adjustments: Step-size adaptation, Kriging metamodeling, and Steady-State Parallelization. We show that all these measures contribute to the acceleration of the SMS-EMOA on continuous benchmark problems as well as on a application problem – the quantum mechanical optimal control with shaped laser pulses.

Keywords

SMS-EMOA Evolutionary multiobjective optimization Expensive evaluation Self-adaptation Metamodels. 

References

  1. Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2000). A fast and elitist multi-objective genetic algorithm nsga-ii. TR 2000001, KanGAL, Kanpur, India.Google Scholar
  2. Emmerich, M. & Deutz, A. (2007). Test Problems based on Lamé Superspheres. In S. Obayashi et al. (Eds.), EMO07, LNCS 4403 (pp. 922–936). Springer.Google Scholar
  3. Emmerich, M. & Naujoks, B. (2004). Metamodel-assisted multiobjective optimisation strategies and their application in airfoil design. In I. C. Parmee (Ed.), Adaptive Computing in Design and Manufacture VI (pp. 249–260). Springer.Google Scholar
  4. Emmerich, M., Giannakoglou, K., & Naujoks, B. (2006). Single-and Multiobjective Optimization Assisted by Gaussian Random Field Metamodels. IEEE-Transactions of Evolutionary Computing, 10(4), 421–439.CrossRefGoogle Scholar
  5. Giotis, A., Giannakoglou, K., & Periaux, J. (2000). A reduced-cost multi-objective optimization method based on the pareto front technique, neural networks and pvm. In ECCOMAS 2000, Barcelona.Google Scholar
  6. Igel, C., Suttorp, T., & Hansen, N. (2006). A computational efficient covariance matrix update and a (1+1)-cma for evolution strategies. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2006) (pp. 453–460). ACM.Google Scholar
  7. Jeong, S., Minemura, Y., & Obayashi, S. (2006). Optimization of combustion chamber for diesel engine using kriging model. Journal of Fluid Science and Technology, 1(2), 138–146.CrossRefGoogle Scholar
  8. Knowles, J. & Hughes, E. (2005). Multiobjective optimization on a budget of 250 evaluations. In C. A. Coello Coello, A. Hernandez Aguirre, E. Zitzler (Eds.), EMO 2005 (pp. 176–190). Guanajuato, Mexico: Springer, Lecture Notes in Computer Science.Google Scholar
  9. Emmerich, M., & Beume, N., & Boris, N. (2005). An emo algorithm using the hypervolume measure as selection criterion. In EMO 2005 (pp. 62–76). Guanajuato, Mexico: Springer, Lecture Notes in Computer Science.Google Scholar
  10. Nain, P. K. S. & Deb, K. (2003). Computationally effective search and optimization procedure using coarse to fine approximations. In Proceedings of the Congress on Evolutionary Computation (CEC-2003) (pp. 2081–2088). Canberra, Australia.Google Scholar
  11. Naujoks, B., Beume, N., & Emmerich, M. (2005). Metamodel-assisted sms-emoa applied to airfoil optimization tasks. In R. Schilling et al. (Ed.), Proceedings EUROGEN’05 (CD-ROM). FLM. TU Münich.Google Scholar
  12. Shir, O. M., Emmerich, M., Bäck, T., Vrakking, M. J. J. (2007). The application of evolutionary multi-criteria optimization to dynamic molecular alignment. In To appear in the proceedings of IEEE-CEC 2007. Singapore: IEEE.Google Scholar
  13. Zitzler, E. (1998). Evolutionary Algorithms for Multiobjective Optimization. Ph.D. thesis, ETH Zürich, Switzerland.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jan-Willem Klinkenberg
  • Michael T. M. Emmerich
    • 1
  • André H. Deutz
  • Ofer M. Shir
  • Thomas Bäck
  1. 1.Leiden Institute for Advanced Computer Science (LIACS)Leiden UniversityLeidenThe Netherlands

Personalised recommendations