Particle swarm optimization (PSO) is becoming one of the most important swarm intelligent paradigms for solving global optimization problems. Although some progress has been made to improve PSO algorithms over the last two decades, additional work is still needed to balance parameters to achieve better numerical properties of accuracy, efficiency, and stability. In the optimal PSO algorithm, the optimal weightings of (√ 5 − 1)/2 and (3 − √5)/2 are used for the cognitive factor and the social factor, respectively. By the same token, the same optimal weightings have been applied for intensification searches and diversification searches, respectively. Perturbation and constriction effects are optimally balanced. Simulations of the de Jong, the Rosenbrock, and the Griewank functions show that the optimal PSO algorithm indeed achieves better numerical properties and outperforms the canonical PSO algorithm.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Optimized Algorithm for Particle Swarm Optimization


    Beteiligte:
    Fuzhang Zhao (Autor:in)

    Erscheinungsdatum :

    04.02.2016


    Anmerkungen:

    oai:zenodo.org:1112117



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Particle Swarm Optimization Algorithm

    Chen, G.-c. / Yu, J.-s. | British Library Online Contents | 2005


    Compact Particle Swarm Optimization Algorithm

    Yu, L. / Zheng, Q. / Zhewen, S. | British Library Online Contents | 2006


    Optimized control of multi-terminal DC GridsUsing particle swarm optimization

    Rouzbehi, Kumars / Miranian, Arash / Luna Alloza, Álvaro et al. | BASE | 2013

    Freier Zugriff

    Iris recognition using Gabor filters optimized by the particle swarm algorithm

    Tsai, C.-C. / Taur, J.-S. / Tao, C.-W. | British Library Online Contents | 2009


    Improved multi-objective particle swarm optimization algorithm

    Baoning, L. / Weiguo, Z. / Guangwen, L. et al. | British Library Online Contents | 2013