Metaheuristics pp 245-260

Part of the Operations Research/Computer Science Interfaces Series book series (ORCS, volume 39) | Cite as

A Study of Canonical GAs for NSOPs

Panmictic versus Decentralized Genetic Algorithms for Non-Stationary Problems
  • Enrique Alba
  • Juan F. Saucedo Badia
  • Gabriel Luque

Abstract

In order to solve a Non-Stationary Optimization Problem (NSOP) it is necessary that the used algorithms have a set of suitable properties for being able to dynamically adapt the search to the changing fitness landscape. Our aim in this work is to improve our knowledge of existing canonical algorithms (steady-state, generational, and structured –cellular– genetic algorithms) in such a scenario. We study the behavior of these algorithms in a basic Dynamic Knapsack Problem, and utilize quantitative metrics for analyzing the results. In this work, we analyze the role of the mutation operator in the three algorithms and the impact of the frequency of dynamic changes in the resulting difficulty of the problem. Our conclusions outline that the steady-state GA is the best in fast adapting its search to a new problem definition, while the cellular GA is the best in preserving diversity to finally get accurate solutions. The generational GA is a tradeoff algorithm showing performances in between the other two.

Keywords

Non-Stationary Problem Dynamic Knapsack Problem Cellular GA 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Alba, E. and Saucedo, J. (2005). Panmictic versus decentralized genetic algorithms for non-stationary problems. In Procs. the Sixth MIC. Electronic publication.Google Scholar
  2. Alba, E. and Troya, J. M. (2000). Cellular evolutionary algorithms: Evaluating the influence of ratio. In Schoenauer, Marc, Deb, K., and et al., editors, Proc. of PPSN VI, volume 1917 of LNCS, pages 29–38, France. Springer.Google Scholar
  3. Alba, E. and Troya, J. M. (2002). Improving flexibility and efficiency by adding parallelism to genetic algorithms. Statistics and Computing, 12(2):91–114.CrossRefGoogle Scholar
  4. Andrews, M. and Tuson, A. (2003). Diversity does not necessarily imply adaptability. In Barry, Alwyn M., editor, GECCO 2003: Proceedings of the Bird of a Feather Workshops, Genetic and Evolutionary Computation Conference, pages 118–122, Chigaco. AAAI.Google Scholar
  5. Bäck, T., Fogel, D. B., and Michalewicz, Z., editors (1997). Handbook of Evolutionary Computation. Oxford University Press.Google Scholar
  6. Branke, J. (2001). Evolutionary Optimization in Dynamic Environments. Klüwer Academic Publishers.Google Scholar
  7. Dasgupta, D. and McGregor, D. R. (1992). Nonstationary function optimization using the structured genetic algorithm. In Männer, Reinhard and Manderick, B., editors, Proc. of PPSN II, pages 145–154, Amsterdan, Holand. Elsevier Science Publishers, B. V.Google Scholar
  8. Ghosh, A., Tsutsui, S., and Tanaka, H. (1998). Function optimization in nonstationary environment using steady state genetic algorithms with aging of individuals. In Proc. of CEC’98, pages 666–671. IEEE Press.Google Scholar
  9. Goldberg, D. E. and Smith, R. E. (1987). Nonstationary function optimization using genetic algorithms with dominance and diploidy. In Grefenstette, J. J., editor, Proc. of ICGA’87, pages 59–68. Lawrence Erlbaum Associates.Google Scholar
  10. Lewis, J., Hart, E., and Ritchie, G. (1998). A comparison of dominance mechanisms and simple mutation on non-stationary problems. In Eiben, Agoston E., Bäck, T., and et al., editors, Proc. of PPSN V, volume 1498 of LNCS, pages 139–148, Berlin, Germany. Springer.Google Scholar
  11. Manderick, B. and Spiessens, P. (1989). Fine-grained parallel genetic algorithms. In Schaffer, J. D., editor, Proc. of ICGA’89, pages 428–433, San Mateo, CA, USA. Morgan Kaufmann.Google Scholar
  12. Mori, N., Kita, H., and Y, Nishikawa (1998). Adaptation to a changing environment by means of the feedback thermodynamical genetic algorithm. In Eiben, Agoston E., Bäck, T., and et al., editors, Proc. of PPSN V, volume 1498 of LNCS, pages 149–158, Berlin, Germany. Springer.Google Scholar
  13. Morrison, R. W. (2003). Performance measurement in dynamic environments. In Barry, Alwyn M., editor, GECCO 2003: Proceedings of the Bird of a Feather Workshops, Genetic and Evolutionary Computation Conference, pages 99–102, Chicago. AAAI.Google Scholar
  14. Ryan, C. (1997). Diploidy without dominance. In Alander, Jarmo T., editor, Proc. of the Third Nordic Workshop on Genetic Algorithms and their Applications, pages 63–70, Vaasa, Finnland. Department of Information Technology and Production Economics, University of Vaasa.Google Scholar
  15. Salomon, R. and Eggenberger, P. (1998). Adaptation on the evolutionary time scale: A working hypothesis and basic experiments. In Hao, J.-K., Lutton, Evelyne, and et al., editors, Proc. of the Third AE’98, volume 1363 of LNCS, pages 251–262, France. Springer.Google Scholar
  16. Sarma, J. and De Jong, K. A. (1996). An analysis of the effect of the neighborhood size and shape on local selection algorithms. In Voigt, Hans-Michael, Ebeling, Werner, and et al., editors, Proc. of PPSN IV, volume 1141 of LNCS, pages 236–244, Berlin, Germany. Springer.Google Scholar
  17. Sarma, J. and De Jong, K. A. (1999). The behavior of spatially distributed evolutionary algorithms in non-stationary environments. In Banzhaf, Wolfgang, Daida, J. M., Eiben, Agoston E., Garzon, Max H., Honavar, Vasant, Jakiela, Mark, and Smith, R. E., editors, Proc. of GECCO’99, pages 572–578, Orlando, FL, USA. Morgan Kaufmann.Google Scholar
  18. Smith, J. E. and Vavak, F. (1999). Replacement strategies in steady state genetic algorithms: dynamic environments. Computing and Information Technology, 7(1):49–60.Google Scholar
  19. Syswerda, G. (1991). A study of reproduction in generational and steady-state genetic algorithms. In Rawlins, Gregory J., editor, Proc. of FOGA’91, pages 94–101, San Mateo, CA, USA. Morgan Kaufmann.Google Scholar
  20. Vavak, F. and Fogarty, T. C. (1996). Comparison of steady state and generational gas for use in nonstationary environments. In Proc. of CEC’96, pages 192–195. IEEE Press.Google Scholar
  21. Weicker, K. (2000). An analysis of dynamic severity and population size. In Schoenauer, Marc, Deb, K., and et al., editors, Proc. of PPSN VI, volume 1917 of LNCS, pages 159–168, France. Springer.Google Scholar
  22. Weicker, K. (2002). Performance measures for dynamic environments. In Merelo Guervós, Juan Julián, Adamidis, Panagiotis, Beyer, Hans-Georg, Fernández-Villacañas, José-Luis, and Schwefel, Hans-Paul, editors, Parallel Problem Solving from Nature – PPSN VII, pages 64–73, Berlin. Springer.Google Scholar
  23. Whitley, D. (1989). The GENITOR algorithm and selection pressure: Why rank-based allocation of reproductive trials is best. In Schaffer, J. D., editor, Proc. of ICGA’89, pages 116–121, San Mateo, CA, USA. Morgan Kaufmann.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Enrique Alba
    • 1
  • Juan F. Saucedo Badia
    • 1
  • Gabriel Luque
    • 1
  1. 1.Departamento de Lenguajes y Ciencias de la ComputaciónE.T.S. Ingeniería InformáticaCampus de Teatinos(SPAIN)

Personalised recommendations