A hybrid particle swarm optimization with crisscross learning strategy. (October 2021)

• Record Type: Journal Article
• Authors: Liang, Baoxian; Zhao, Yunlong; Li, Yang
• Is Part Of: Engineering applications of artificial intelligence. Volume 105(2021)
• Publication Date: 2021-10
• Subjects: Crisscross learning -- Stochastic example learning -- Particle swarm optimization (PSO); Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104418
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: As an efficient and simple optimization algorithm, particle swarm optimization (PSO) has been widely applied to solve various real optimization problems. However, avoiding premature convergence and balancing the global exploration and local exploitation capabilities of the PSO remains two crucial problems. To overcome these drawbacks of PSO, a hybrid particle swarm optimization with crisscross learning strategy (PSO-CL) algorithm is proposed in this paper. In PSO-CL, in order to well balance the global exploration and local exploitation capabilities of PSO, a search direction adjustment mechanism based on subpopulation division operation is proposed. Meantime, to avoid the premature convergence and enhance the global search ability, a crossover-based comprehensive learning strategy (CCL) is adopted. Additionally, a stochastic example learning strategy (SEL) is introduced, which can assist collective information to be spread among separate sub-swarms, improve the local exploitation ability of the algorithm. 15 classic benchmark functions, CEC2017 test suite and two real-world optimization problems are utilized to verify the promising performance of PSO-CL, experimental results and statistical analysis indicate that PSO-CL has competitive performance compared with state-of-the-art PSO variants. Graphical abstract: Highlights: A search direction adjustment mechanism based on subpopulation division operation. A crossover-based comprehensive learning strategy is presented, which can enhance the diversity of swarm. A stochastic example learning strategy is introduced to further enhance the convergence precise.