Improving migration by diversity

We present an improvement to distributed GAs based on migration of individuals between several concurrently evolving populations. The idea behind our improvement is to not only use the fitness of an individual as criterion for selecting the individuals that migrate, but also to consider the diversity of individuals versus the currently best individual. We experimentally show that a distributed GA using a weighted sum of fitness and a diversity measure for selecting migrating individuals finds the known optimal solutions to benchmark problems from literature (that offer a lot of local optima) on average substantially faster than the distributed GA using only fitness for selection. In addition, the run times of several runs of the distributed GA to the same problem instance vary much less with our improvement than in the base case, thus resulting in a more stable behavior of a distributed GA of this type.

[1]  Jörg Denzinger,et al.  On cooperation between evolutionary algorithms and other search paradigms , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[2]  Jörg Denzinger.  Knowledge-Based Distributed Search Using Teamwork , 1995, ICMAS.

[3]  Alan S. Perelson,et al.  Searching for Diverse, Cooperative Populations with Genetic Algorithms , 1993, Evolutionary Computation.

[4]  Jörg Denzinger.  Conflict handling in collaborative search , 2001 .

[5]  Erick Cant,et al.  Designing Efficient And Accurate Parallel Genetic Algorithms , 1999 .

[6]  Erik D. Goodman,et al.  An Injection Island GA for Flywheel Design Optimization , 1997 .

[7]  John J. Grefenstette,et al.  ROBOT LEARNING WITH PARALLEL GENETIC ALGORITHMS ON NETWORKED COMPUTERS , 1995 .

[8]  John H. Holland,et al.  Distributed genetic algorithms for function optimization , 1989 .

[9]  João Pedro Pedroso,et al.  Niche Search: An Evolutionary Algorithm for Global Optimisation , 1996, PPSN.

[10]  Erick Cantú-Paz.  Designing Efficient and Accurate Parallel Genetic Algorithms , 1999 .

[11]  Edwin D. de Jong,et al.  Reducing bloat and promoting diversity using multi-objective methods , 2001 .

[12]  Paul Bryant Grosso,et al.  Computer Simulations of Genetic Adaptation: Parallel Subcomponent Interaction in a Multilocus Model , 1985 .

[13]  Konstantinos G. Margaritis,et al.  An Experimental Study of Benchmarking Functions for Genetic Algorithms , 2002, Int. J. Comput. Math..

[14]  J. Urgen Lind,et al.  Twlib { a Library for Distributed Search Applications , 1996 .

[15]  J. A. Robinson,et al.  A Machine-Oriented Logic Based on the Resolution Principle , 1965, JACM.

[16]  Erick Cantú-Paz,et al.  Migration Policies, Selection Pressure, and Parallel Evolutionary Algorithms , 2001, J. Heuristics.

[17]  Wolfgang Ertel.  Parallele Suche mit randomisiertem Wettbewerb in Inferenzsystemen , 1993, DISKI.