Advertisement

Evolutionary Algorithms for Dynamic Environments: Prediction Using Linear Regression and Markov Chains

  • Anabela Simões
  • Ernesto Costa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5199)

Abstract

In this work we investigate the use of prediction mechanisms in Evolutionary Algorithms for dynamic environments. These mechanisms, linear regression and Markov chains, are used to estimate the generation when a change in the environment will occur, and also to predict to which state (or states) the environment may change, respectively. Different types of environmental changes were studied. A memory-based evolutionary algorithm empowered by these two techniques was successfully applied to several instances of the dynamic bit matching problem.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jin, Y., Branke, J.: Evolutionary optimization in uncertain environments: a survey. IEEE Transactions on Evolutionary Computation 9(3), 303–317 (2005)CrossRefGoogle Scholar
  2. 2.
    Yang, S.: Explicit memory schemes for evolutionary algorithms in dynamic environments. In: Yang, S., Ong, Y.S., Jin, Y. (eds.) Evolutionary Computation in Dynamic and Uncertain Environments, pp. 3–28. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Simões, A., Costa, E.: Evolutionary algorithms for dynamic environments: prediction using linear regression and markov chains. Technical Report TR 2008/01, CISUC (2008)Google Scholar
  4. 4.
    Branke, J., Mattfeld, D.: Anticipation in dynamic optimization: The scheduling case. In: Schoenauer, M., Deb, K., Rudolph, G., Yao, X., Lutton, E., Merelo, J., Schwefel, H.P. (eds.) PPSN VI 2000. LNCS, vol. 1917, pp. 253–262. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  5. 5.
    Stroud, P.D.: Kalman-extended genetic algorithm for search in nonstationary environments with noisy fitness evaluations. IEEE Transactions on Evolutionary Computation 5(1), 66–77 (2001)CrossRefGoogle Scholar
  6. 6.
    van Hemert, J., Hoyweghen, C.V., Lukshandl, E., Verbeeck, K.: A futurist approach to dynamic environments. In: GECCO Workshop on Evolutionary Algorithms for Dynamic Optimization Problems, pp. 35–38 (2001)Google Scholar
  7. 7.
    Bosman, P.: Learning, anticipation and time-deception in evolutionary online dynamic optimization. In: Yang, S., Branke, J. (eds.) GECCO Workshop on Evolutionary Algorithms for Dynamic Optimization (2005)Google Scholar
  8. 8.
    Bosman, P.A.N.: Learning and anticipation in online dynamic optimization. In: Yang, S., Ong, Y.S., Jin, Y. (eds.) Evolutionary Computation in Dynamic and Uncertain Environments. Springer, Heidelberg (2007)Google Scholar
  9. 9.
    Bird, S., Xiaodong, L.: Using regression to improve local convergence. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2007), pp. 592–599. IEEE Press, Los Alamitos (2007)CrossRefGoogle Scholar
  10. 10.
    Norris, J.R.: Markov Chains. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, Cambridge (1997)CrossRefzbMATHGoogle Scholar
  11. 11.
    Branke, J.: Memory enhanced evolutionary algorithms for changing optimization problems. In: IEEE Congress on Evolutionary Computation (CEC 1999), pp. 1875–1882. IEEE Press, Los Alamitos (1999)Google Scholar
  12. 12.
    Simões, A., Costa, E.: Improving memory’s usage in evolutionary algorithms for changing environments. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2007). IEEE Press, Los Alamitos (2007)Google Scholar
  13. 13.
    Simões, A., Costa, E.: An immune system-based genetic algorithm to deal with dynamic environments: Diversity and memory. In: Proc. of the 6th Int. Conf. on Artificial Neural Networks, pp. 168–174. Springer, Heidelberg (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Anabela Simões
    • 1
    • 2
  • Ernesto Costa
    • 2
  1. 1.Department of Informatics and Systems Engineering, Coimbra PolytechnicPortugal
  2. 2.Centre of Informatics and Systems of the University of CoimbraPortugal

Personalised recommendations