GEATbx: Options 7 Competition options





7 Competition options
Competition.Do
This option switches competition between subpopulations on or off. Competition is executed by compete. Competition is an extension of the regional population model.
- Default value: 0
- Type: integer in {0, 1}
- Two variants are available:
- 0: no competition
- 1: do competition between subpopulations
- Example - switch competition on:
GeaOpt = geaoptset(GeaOpt, 'Competition.Do', 1);
- Competition without migration (Migration.Do) doesn't make sense. When only one subpopulation is defined (see NumberSubpopulation) no competition takes place.
- Option number in previous versions: 36 (2.x), not available (1.x)
Competition.Interval
This option specifies how often a competition takes place. Thus, the frequency of competition is defined.
- Default value: 4
- Type: positive integer in [1, Inf]
- Example - set competition interval to every 10 generations:
GeaOpt = geaoptset(GeaOpt, 'Competition.Interval', 10);
- A competition takes place (that means the function compete is called) when the reminder of Run.Generation and Competition.Interval is zero.
- Option number in previous versions: 38 (2.x), not available (1.x)
Competition.Rate
This option defines the fraction of every subpopulation to be transferred from unsuccessful subpopulations during a competition.
- Default value: 0.1
- Type: scalar in [0, 1)
- Example - set competition rate to 5%:
GeaOpt = geaoptset(GeaOpt, 'Competition.Rate', 0.05);
- Option number in previous versions: 37 (2.x), not available (1.x)
Competition.SubpopMinimum
This option defines the minimal number of individuals per subpopulation. When a subpopulation contains this minimal number of individuals, no further individuals are transferred to successful subpopulations.
- Default value: 5
- Type: positive integer in [1, Inf]
- Example - set minimal number of individuals to 10 individuals:
GeaOpt = geaoptset(GeaOpt, 'Competition.SubpopMinimum', 10);
- Option number in previous versions: 39 (2.x), not available (1.x)






This document is part of
version 3.8 of the
GEATbx: Genetic and Evolutionary Algorithm Toolbox for use with Matlab -
www.geatbx.com.
The Genetic and Evolutionary Algorithm Toolbox is
not public domain.
© 1994-2006 Hartmut Pohlheim, All Rights Reserved,
(support@geatbx.com).