摘要
为了平衡多目标粒子群算法的多样性和收敛性,提出一种基于多样性检测的多子群多目标粒子群算法.首先,将多样性检测方法引入到多目标粒子群算法中,并结合多目标粒子群算法的特点进行改进.然后,将种群分为两个不同分工的子群,一个子群保持较好的多样性,在搜索空间进行全局搜索;另一个子群保持较好的收敛性,在Pareto前沿附近进行局部搜索.最后,根据多样性度量指标调整两个子群的搜索行为,以达到兼顾多样性和收敛性的目的.在标准测试问题上的仿真结果表明了所提算法的有效性.
In order to keep the balance between the diversity and convergence, a bi-group multi-objective particle swarm optimization algorithm based on diversity metric is propose. Firstly, a diversity metric is introduced to multi-objective particle swarm optimization（MOPSO） algorithm and improved based on its characteristics. Then, the whole swarm is divided to two bi-groups with different searching tasks. One of the groups keeps population＇s diversity during evolution to search better in the whole search space. The other group keeps its convergence to local search nearby the Pareto front.Further more, the searching behavior of the groups based on the diversity metric is adjusted to balance the diversity and convergence. The simulations on several standard test functions verify the effectiveness of the proposed method.
出处
《控制与决策》
EI
CSCD
北大核心
2017年第12期2268-2272,共5页
Control and Decision
基金
国家自然科学基金项目(61374154)
关键词
多样性
子群
自适应
多目标优化
粒子群优化
diversity, bi-group
adaptive adjustment
multi-objective optimization
particle swarm optimization
