Abstract
Social learning particle swarm optimization (SL-PSO) allows individuals to learn from others to improve the scalability with easy parameter settings. However, it still suffers from the poor convergence for those multi-modal problems due to the loss of swarm diversity. To improve both the diversity and the convergence, this paper proposes a novel algorithm to apply the mechanism of molecular interactions to SL-PSO, in which the molecular attraction aims to improve the convergence, and the molecular repulsion intends to enhance the diversity. In the experiments, we compare our algorithm with the SL-PSO algorithm and other representative PSO and evolutionary algorithms on 49 benchmark functions. The results show the performance of the proposed algorithm is better than that of the SL-PSO algorithm and other representative PSO and evolutionary algorithms on average. This work builds the solid foundation for the integration of the molecular interaction mechanism with PSO and other optimization algorithms.
Highlights
Particle swarm optimization (PSO) is a computational method that seeks the optima of a problem by iteratively updating of particles’ positions
Except for the MISL-PSO algorithm, the Social learning particle swarm optimization (SL-PSO) algorithm and the AR-gravitational search algorithm (GSA) algorithm, a state-of-the-art PSO variant is selected for the comparison, which uses ring topology and elitist learning as non-greedy strategies in place of the traditional update method based on Gbest and Pbest, called the elitist learning PSO algorithm with scaling mutation and ring topology(LSERPSO) [49]
SL-PSO improves the traditional PSO by learning bet- easy parameter settings and improved performance. In this ter particles instead of the local and global optima for paper, based on SL-PSO, we introduce the molecular mechanism into SL-PSO to further improve the performance by enhancing both of the convergence and the diversity
Summary
Particle swarm optimization (PSO) is a computational method that seeks the optima of a problem by iteratively updating of particles’ positions. For the purpose of easy parameters setting and the performance enhancement, social learning PSO was proposed, in which each particle learns from one of the better particles in the current swarm and only one dimension-dependent parameter control method is applied [10] It still may suffer from the tradeoff between the diversity and the convergence. The MISL-PSO algorithm takes advantage of molecular interaction forces to adjust the position of particles to achieve a balance between the convergence and the diversity. For this goal, three key issues need to be studied: (1) the determination of the range of the particle interaction fields; (2) the determination of attraction forces between particles; (3) the determination of repulsion forces between particles
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
