摘要
针对NP-hard组合优化及粒子群算法离散化问题,提出一种当代学习自适应混合离散粒子群算法对其进行求解.依据粒子多样性的变化规律,引入自适应扰动算子,以保持种群进化能力;根据成功的粒子群社会学习能力和个体学习能力,提出粒子群当代学习因子以体现粒子当代学习能力,进而改进其运动方程,使算法稳定性得到提高;最后融入近邻搜索变异策略,提升算法局部求精能力.实验表明:当代学习自适应混合离散粒子群算法较其他三种离散粒子群算法在解的质量方面有所改进,并首次在算法稳定性上得到了较大进步,为离散粒子群算法稳定性研究提供了新的思路.
This paper presents a new current learning adaptive hybrid discrete particle swarm optimization algorithm for NP-hard combinatorial optimization problem and particle swarm discretization problem. Adaptive perturbation factor is introduced according to the population heterogeneity to keep particle swarm evolutional capability. Based on the excellent performance of particle swarm society learning ability and individual learning ability in Discrete Particle Swarm Optimization （DPSO）, we propose a new conception current learning factor to take up the DPSO kinetic equation, and then the algorithm stability is improved greatly. Finally nearby neighbor mutant strategy is added to increase local search capabilities. The experiment results are shown that solution quality of Current Learning Adaptive Hybrid Discrete Particle Swarm Optimization Algorithm （CLAHDPSO） is better than other three DPSO, and it＇s the first time to contribute to algorithm stability. Additionally it＇s also a novel ideal to research the stability of DPSO.
出处
《小型微型计算机系统》
CSCD
北大核心
2009年第9期1800-1804,共5页
Journal of Chinese Computer Systems
基金
国家基础研究项目(A1420060159)资助
NSFC重大研究计划资助项目(90820302)资助
国家博士点基金项目(200805330005)资助
关键词
离散粒子群
自适应扰动算子
当代学习
变异策略
discrete particle swarm optimization algorithm
adaptive perturbation factor
current learning
mutant strategy
