Use of dominance to improve performance or increase search space in genetic algorithms

摘要

Methods, systems, and articles of manufacture utilizing the biological principle of dominance to affect the operation of a genetic algorithm are provided. The genetic algorithm may be used to select a multi-parameter solution set to a user-defined problem, with each parameter modeled as a gene. Dominance may be introduced by associating a dominance attribute with one or more gene values (i.e., traits), for example, that are known to lead to good solution sets, allowing the corresponding gene values to be specified as dominant or recessive. By specifying the known good gene values as dominant, system performance may be optimized as the genetic algorithm may quickly arrive at a good solution set (e.g., due to the known good value appearing more often in future generations). On the other hand, by specifying the known good gene value as recessive, the search space may be increased as the genetic algorithm may evaluate a larger number of possible solution sets (e.g., due to the known good value appearing less often in future generations).