摘要
为了避免粒子群优化算法早熟收敛,本文提出了一种改进的粒子群优化算法。为保持解的多样性,采用种群分组策略,并根据邻域内粒子的选择概率,选择粒子。仿真实验结果表明,本文算法优于GPSO算法。
In order to avoid premature convergence of Particle Swarm Optimization, a new IX30 algorithm is proposed. To keep the diversity of the solutions, particles grouping strategy is adopted, and particle is selected according to the selection probability in neighborhood. Simulation results demonstrate that our approach outperforms GPSO algorithms.
出处
《山东工业技术》
2013年第13期203-203,202,共2页
Journal of Shandong Industrial Technology
关键词
粒子群
多峰问题
邻域
Particle swarm
Muhimodal problem
Neighborhood