A Method to Reuse Old Populations in Genetic Algorithms
In this paper a method to increase the optimization ability of genetic algorithms (GAs) is proposed. To promote population diversity, a fraction of the worst individuals of the current population is replaced by individuals from an older population. To experimentally validate the approach we have used a set of well-known benchmark problems of tunable difficulty for GAs. Standard GA with and without elitism and steady state GA have been augmented with the proposed method. The obtained results show that the algorithms augmented with the proposed method perform better than the not-augmented algorithms or have the same performances. Furthermore, the proposed method depends on two parameters: one of them regulates the size of the fraction of the population replaced and the other one decides the “age” of the population used for the replacement. Experimental results indicate that better performances have been achieved with high values of the former parameter and low values of the latter one.
KeywordsGenetic Algorithm Refresh Rate Good Performer Small Medium Clonal Selection Algorithm
Unable to display preview. Download preview PDF.
- 2.De Castro, L.N., Von Zuben, F.J.: The clonal selection algorithm with engineering applications. In: GECCO 2002 - Workshop Proceedings, pp. 36–37. Morgan Kaufmann (2002)Google Scholar
- 5.Greensmith, J., Whitbrook, A.M., Aickelin, U.: Artificial immune systems (2010). Computing Research Repository (CoRR), abs/1006.4949 (2010), http://arxiv.org/abs/1006.4949
- 6.Holland, J.H.: Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor (1975)Google Scholar
- 7.Kauffman, S.A.: Adaptation on rugged fitness landscapes. In: Stein, D. (ed.) Lectures in the Sciences of Complexity, Redwood City. SFI Studies in the Sciences of Complexity, Lecture, vol. I, Addison-Wesley (1989)Google Scholar
- 9.Louis, S., Li, G.: Augmenting genetic algorithms with memory to solve traveling salesman problems. In: Proceedings of the Joint Conference on Information Sciences, pp. 108–111. Duke University Press (1997)Google Scholar
- 10.Moore, D.S.: The Basic Practice of Statistics, 2nd edn. W. H. Freeman & Co., New York (1999)Google Scholar
- 11.Schaffer, J.D., Eshelman, L.J.: On crossover as an evolutionary viable strategy. In: Belew, R.K., Booker, L.B. (eds.) Proceedings of the 4th International Conference on Genetic Algorithms, pp. 61–68. Morgan Kaufmann, San Francisco (1991)Google Scholar
- 12.Sheppard, J., Salzberg, S.: Combining genetic algorithms with memory based reasoning. In: Proceedings of the Sixth International Conference on Genetic Algorithms, pp. 452–459. Morgan Kaufmann (1995)Google Scholar
- 13.Wiering, M.: Memory-based memetic algorithms. In: Nowe, A., Lenaerts, T., Steenhout, K. (eds.) Benelearn 2004: Proceedings of the Thirteenth Belgian-Dutch Conference on Machine Learning, pp. 191–198 (2004)Google Scholar