Dual-Stage Hybrid Learning Particle Swarm Optimization Algorithm for Global Optimization Problems

Particle swarm optimization (PSO) is a type of intelligence algorithm that frequently used to resolve specific global problems due its rapid convergence and ease operation. However, PSO still has certain deficiencies, such as poor trade-off between exploration exploitation premature convergence. Hence, this paper proposes dual-stage hybrid learning particle (DHLPSO). In the algorithm, iterative process partitioned into two stages. The strategy at each stage emphasizes exploitation, respectively. first stage, increase population variety, Manhattan distance based proposed. strategy, chooses furthest better for learning. second an excellent example adopted perform local operations on population, in which learns from optimal particle. Utilizing Gaussian mutation algorithm's searchability particular multimodal functions significantly enhanced. On benchmark CEC 2013, DHLPSO evaluated alongside other variants already existence. comparison results clearly demonstrate that, compared cutting-edge variations, implements highly competitive performance handling problems.