2015 | OriginalPaper | Buchkapitel
An Improved Hybrid PSO Based on ARPSO and the Quasi-Newton Method
verfasst von : Fei Han, Qing Liu
Erschienen in: Advances in Swarm and Computational Intelligence
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Although attractive and repulsive particle swarm optimization (ARPSO) algorithm keeps the diversity of the swarm adaptively to avoid premature convergence, its search performance is still restricted because of its stochastic search mechanism. In this study, a new hybrid algorithm combining ARPSO with the Quasi-Newton method is proposed to improve the search ability of the swarm. In the proposed algorithm, ARPSO keeps the reasonable search space by controlling the swarm not to lose its diversity, while the Quasi-Newton method is used to perform local search efficiently. The Quasi-Newton method makes the hybrid algorithm converge to optimal solution accurately. The experimental results verify that the proposed hybrid PSO has better convergence performance than some classic PSO algorithms.