Finding robust optima wth a diploid genetic algorithm

Shane Lee, Hefin Rowlands

    Research output: Contribution to journalArticlepeer-review

    1 Citation (Scopus)

    Abstract

    Genetic algorithms are generally used to search for global optima. However, for many engineering /simulation applications a robust solution is desired, which may not correspond to the global optimum of the given problem. This paper describes a genetic algorithm using diploid chromosomes, which favours robust local optima rather than a less robust global optimum in a problem space. Diploid chromosomes are created with two binary haploid chromosomes, which are used to create a schema. The schema then used to measure the fitness of a family of solutions. The results of experiments using a bi-modal fitness function with one local optimum and a fitter less robust global optimum show that the optima in the problem space representing the more robust solution is found almost 100% of the time.

    Original languageEnglish
    Pages (from-to)73-79
    Number of pages7
    JournalInternational Journal of Simulation: Systems, Science and Technology
    Volume6
    Issue number9
    Publication statusPublished - 1 Aug 2005

    Fingerprint

    Dive into the research topics of 'Finding robust optima wth a diploid genetic algorithm'. Together they form a unique fingerprint.

    Cite this