Bimodal Performance Profile of Evolutionary Search and the Effects of Crossover

  • M. Oates
  • J. Smedley
  • D. Corne
  • R. Loader
Chapter
Part of the Natural Computing Series book series (NCS)

Abstract

Tunable performance profiles for evolutionary search on instances of the adaptive distributed database management problem have previously been plotted and published by the authors. This demonstrates a bimodal feature of convergence time with respect to population size and mutation rate. Preliminary results on other problems (one-max, De Jong functions, etc.) led to the tentative conclusion that the features of the complex profile discovered could indeed be generic, and four key hypotheses were presented. These covered the effects of problem complexity and evaluation limit on optimal and non-optimal mutation rates. This paper expands significantly on these results looking in more detail at the one-max and royal staircase problems, and demonstrates the effect of various rates of crossover on the performance profile of evolutionary search. Crucially, these results continue to demonstrate the bimodal feature and show that reduced levels of crossover extend the influence of the bimodal region to higher population sizes. A study of the coefficient of variation of convergence time shows importantly that this can be at a minimum at an optimal mutation rate which can also deliver consistent results in a minimum number of evaluations.

Keywords

Bimodal response one-max royal staircase convergence time crossover optimal mutation rate population size 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    T. Bäck. Evolutionary Algorithms in Theory and Practice. Oxford University Press, 1996.MATHGoogle Scholar
  2. 2.
    K. Deb and S. Agrawal. Understanding Interactions Among Genetic Algorithm Parameters. In W. Banzhaf and C. Reeves, editors, Foundations of Genetic Algorithms 5, pages 265–286. Morgan Kaufmann, San Francisco, 1998.Google Scholar
  3. 3.
    D. Goldberg. Genetic Algorithms in Search Optimisation and Machine Learning. Addison—Wesley, Reading, MA, 1989.Google Scholar
  4. 4.
    J. H. Holland. Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor, MI, 1975.Google Scholar
  5. 5.
    Z. Michalewicz. Genetic Algorithms + Data Structures = Evolution Programs. Springer-Verlag, Berlin Heidelberg New York, 3rd edition, 1996.MATHCrossRefGoogle Scholar
  6. 6.
    H. Mühlenbein. How Genetic Algorithms Really Work: I. Mutation and Hillclimbing. In R. Manner and B. Manderick, editors, Proceedings of the 2nd Int’l Conf. on Parallel Problem Solving from Nature, pages 15–25. Elsevier, Amsterdam, 1992.Google Scholar
  7. 7.
    H. Mühlenbein and D. Schlierkamp-Voosen. The Science of Breeding and its application to the Breeder Genetic Algorithm. Evolutionary Computation, 2(3):335–360, 1994.Google Scholar
  8. 8.
    M. Oates. Autonomous Management of Distributed Information Systems using Evolutionary Computing Techniques. In Computing Anticipatory Systems, pages 269–281, 1998.Google Scholar
  9. 9.
    M. Oates and D. Corne. Investigating Evolutionary Approaches to Adaptive Database Management Against Various Quality of Service Metrics. In Proceedings of the 5th Int’l Conf. on Parallel Problem Solving from Nature, LNCS 1498, pages 775–784. Springer-Verlag, Berlin Heidelberg New York, 1998.Google Scholar
  10. 10.
    M. Oates and D. Corne. QoS-based GA Parameter Selection for Autonomously Managed Distributed Information Systems. In Proceedings of the 1998 European Conference on Artificial Intelligence, pages 670–674. IEEE Press, 1998.Google Scholar
  11. 11.
    M. Oates, D. Corne, and R. Loader. Investigating Evolutionary Approaches for SelfAdaptation in Large Distributed Databases. In Proceedings of the 1998 IEEE Int’l Congress on Evolutionary Computation, pages 452–457. IEEE Press, New York, 1998.Google Scholar
  12. 12.
    M. Oates, D. Corne, and R. Loader. Investigation of a Characteristic Bimodal Convergence-time/Mutation-rate Feature in Evolutionary Search. In Proceedings of the 1999 IEEE Int’l Congress on Evolutionary Computation, volume 3, pages 2175– 2182. IEEE Press, New York, 1998.Google Scholar
  13. 13.
    M. Oates, D. Corne, and R. Loader. Skewed Crossover and the Dynamic Distributed Database Problem. In Artificial Neural Nets and Genetic Algorithms, pages 280–287. Springer-Verlag, Vienna New York, 1999.CrossRefGoogle Scholar
  14. 14.
    M. Oates, D. Corne, and R. Loader. Variation in Evolutionary Algorithm Performance Characteristics on the Adaptive Distributed Database Management Problem. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 1999, pages 480–487. Morgan Kaufmann, San Francisco, 1999.Google Scholar
  15. 15.
    G. Syswerda. Uniform Crossover in Genetic Algorithms. In Proceedings of the Third International Conference on Genetic Algorithms, pages 2–9. Morgan Kaufmann, San Francisco, 1989.Google Scholar
  16. 16.
    E. van Nimwegen and J. Crutchfield. Optimizing Epochal Evolutionary Search: Population-Size Dependent Theory. Technical Report 98–10–090, Santa Fe Institute, 1998.Google Scholar
  17. 17.
    E. Van Nimwegen and J. Crutchfield. Optimizing Epochal Evolutionary Search: Population-Size Independent Theory. Technical Report 98–06–046, Santa Fe Institute, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • M. Oates
    • 1
  • J. Smedley
    • 1
  • D. Corne
    • 1
  • R. Loader
    • 1
  1. 1.BT LaboratoriesMartlesham HeathSuffolkUK

Personalised recommendations