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.


    Access

    Download


    Export, share and cite



    Title :

    Optimized Algorithm for Particle Swarm Optimization


    Contributors:

    Publication date :

    2016-02-04


    Remarks:

    oai:zenodo.org:1112117



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    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

    Free access

    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