Self-sampling Strategies for Multimemetic Algorithms in Unstable Computational Environments

  • Rafael Nogueras
  • Carlos Cotta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9108)

Abstract

Optimization algorithms deployed on unstable computational environments must be resilient to the volatility of computing nodes. Different fault-tolerance mechanisms have been proposed for this purpose. We focus on the use of dynamic population sizes in the context of island-based multimemetic algorithms, namely memetic algorithms which explicitly represent and evolve memes alongside solutions. These strategies require the eventual creation of new solutions in order to enlarge island populations, aiming to compensate the loss of information taking place when neighboring computing nodes go down. We study the influence that the mechanism used to create these new individuals has on the performance of the algorithm. To be precise, we consider the use of probabilistic models of the current population which are subsequently sampled in order to produce diverse solutions without distorting the convergence of the population and the progress of the search. We perform an extensive empirical assessment of those strategies on three different problems, considering a simulated computational environment featuring diverse degrees of instability. It is shown that these self-sampling strategies provide a performance improvement with respect to random reinitialization, and that a model using bivariate probabilistic dependencies is more effective in scenarios with large volatility.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alba, E.: Parallel evolutionary algorithms can achieve super-linear performance. Information Processing Letters 82, 7–13 (2002)CrossRefMATHMathSciNetGoogle Scholar
  2. 2.
    Alba, E.: Parallel Metaheuristics: A New Class of Algorithms. Wiley-Interscience (2005)Google Scholar
  3. 3.
    Albert, R., Barabási, A.L.: Statistical mechanics of complex networks. Review of Modern Physics 74(1), 47–97 (2002)CrossRefMATHGoogle Scholar
  4. 4.
    Baluja, S., Davies, S.: Using optimal dependency-trees for combinatorial optimization: Learning the structure of the search space. In: 14th International Conference on Machine Learning, pp. 30–38. Morgan Kaufmann (1997)Google Scholar
  5. 5.
    Bonet, J.S.D., Isbell Jr., C.L., Viola, P.: MIMIC: Finding optima by estimating probability densities. In: Mozer, M., Jordan, M., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 424–430. The MIT Press (1996)Google Scholar
  6. 6.
    Deb, K., Goldberg, D.E.: Analyzing deception in trap functions. In: Whitley, L.D. (ed.) Second Workshop on Foundations of Genetic Algorithms, pp. 93–108. Morgan Kaufmann, Vail (1993)Google Scholar
  7. 7.
    Goldberg, D.E., Deb, K., Horn, J.: Massive multimodality, deception, and genetic algorithms. In: Parallel Problem Solving from Nature – PPSN II, pp. 37–48. Elsevier, Brussels (1992)Google Scholar
  8. 8.
    Hidalgo, J.I., Lanchares, J., Fernández de Vega, F., Lombraña, D.: Is the island model fault tolerant? In: Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation, GECCO 2007, pp. 2737–2744. ACM, New York (2007)CrossRefGoogle Scholar
  9. 9.
    Holm, S.: A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics 6, 65–70 (1979)MATHMathSciNetGoogle Scholar
  10. 10.
    Jiménez Laredo, J.L., Bouvry, P., Lombraña González, D., Fernández de Vega, F., García Arenas, M., Merelo Guervós, J.J., Fernandes, C.M.: Designing robust volunteer-based evolutionary algorithms. Genetic Programming and Evolvable Machines 15(3), 221–244 (2014)CrossRefGoogle Scholar
  11. 11.
    Krasnogor, N., Blackburne, B.P., Burke, E.K., Hirst, J.D.: Multimeme algorithms for protein structure prediction. In: Guervós, J.J.M., Adamidis, P.A., Beyer, H.-G., Fernández-Villacañas, J.-L., Schwefel, H.-P. (eds.) PPSN 2002. LNCS, vol. 2439, pp. 769–778. Springer, Heidelberg (2002)Google Scholar
  12. 12.
    Liu, C., White, R.W., Dumais, S.: Understanding web browsing behaviors through weibull analysis of dwell time. In: Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2010, pp. 379–386. ACM, New York (2010)Google Scholar
  13. 13.
    Milojičić, D.S., Kalogeraki, V., Lukose, R., Nagaraja, K., Pruyne, J., Richard, B., Rollins, S., Xu, Z.: Peer-to-peer computing. Tech. Rep. HPL-2002-57, Hewlett-Packard Labs (2002)Google Scholar
  14. 14.
    Mühlenbein, H., Paaß, G.: From recombination of genes to the estimation of distributions I. Binary parameters. In: Ebeling, W., Rechenberg, I., Voigt, H.-M., Schwefel, H.-P. (eds.) PPSN 1996. LNCS, vol. 1141, pp. 178–187. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  15. 15.
    Neri, F., Cotta, C., Moscato, P.: Handbook of Memetic Algorithms. SCI, vol. 379. Springer, Heidelberg (2013)Google Scholar
  16. 16.
    Nogueras, R., Cotta, C.: Studying fault-tolerance in island-based evolutionary and multimemetic algorithms. Journal of Grid Computing (2015), doi:10.1007/s10723-014-9315-6Google Scholar
  17. 17.
    Nogueras, R., Cotta, C.: An analysis of migration strategies in island-based multimemetic algorithms. In: Bartz-Beielstein, T., Branke, J., Filipič, B., Smith, J. (eds.) PPSN 2014. LNCS, vol. 8672, pp. 731–740. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  18. 18.
    Nogueras, R., Cotta, C.: On meme self-adaptation in spatially-structured multimemetic algorithms. In: Dimov, I., Fidanova, S., Lirkov, I. (eds.) NMA 2014. LNCS, vol. 8962, pp. 70–77. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  19. 19.
    Nogueras, R., Cotta, C.: Self-balancing multimemetic algorithms in dynamic scale-free networks. In: Mora, A.M., Squillero, G. (eds.) EvoApplications 2015. LNCS, vol. 9028, pp. 177–188. Springer, Heidelberg (2015)Google Scholar
  20. 20.
    Ong, Y.S., Lim, M.H., Chen, X.: Memetic computation-past, present and future. IEEE Computational Intelligence Magazine 5(2), 24–31 (2010)CrossRefGoogle Scholar
  21. 21.
    Quade, D.: Using weighted rankings in the analysis of complete blocks with additive block effects. Journal of the American Statistical Association 74, 680–683 (1979)CrossRefMATHMathSciNetGoogle Scholar
  22. 22.
    Sarmenta, L.F.: Bayanihan: Web-based volunteer computing using java. In: Masunaga, Y., Tsukamoto, M. (eds.) WWCA 1998. LNCS, vol. 1368, pp. 444–461. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  23. 23.
    Smith, J.E.: Self-adaptation in evolutionary algorithms for combinatorial optimisation. In: Cotta, C., Sevaux, M., Sörensen, K. (eds.) Adaptive and Multilevel Metaheuristics. SCI, vol. 136, pp. 31–57. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  24. 24.
    Tanese, R.: Distributed genetic algorithms. In: 3rd International Conference on Genetic Algorithms, pp. 434–439. Morgan Kaufmann Publishers Inc., San Francisco (1989)Google Scholar
  25. 25.
    Watson, R.A., Hornby, G.S., Pollack, J.B.: Modeling building-block interdependency. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H.-P. (eds.) PPSN 1998. LNCS, vol. 1498, pp. 97–106. Springer, Heidelberg (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Rafael Nogueras
    • 1
  • Carlos Cotta
    • 1
  1. 1.Dept. Lenguajes y Ciencias de la ComputaciónUniversidad de Málaga, ETSI InformáticaMálagaSpain

Personalised recommendations