摘要
在多目标优化遗传算法中,将整个种群按目标函数值划分成若干子种群,在各子种群内μ个父代经遗传操作产生λ个后代;然后将各子种群的所有父代和后代个体收集起来进行种群排序适应度共享,选取较好的个体组成下一代种群。相邻的非劣解容易分在同一子种群有利于提高搜索效率;各子种群间的遗传操作可采用并行处理;各子种群的所有个体收集起来进行适应度共享有利于维持种群的多样性。最后给出了计算实例。
In multi-objective optimization genetic algorithms, the whole population is sorted with respect to the values of the focused objective function and divided into sub-populations. In each sub-population,μ parents generate λ, offsprings by genetic operators. Then,all individuals are gathered and sorted, the fitness sharing is performed and better individuals are selected to be the next generation. In this approach, the Pareto optimum solutions which are close to each other are collected by one sub-population and using the （μ＋λ） selection strategy increases search efficiency. The genetic operation which is performed in sub-populations is suitable for parallel processing and the fitness sharing of the whole population is conducive to maintaining the diversity of population as well.
出处
《计算机工程与科学》
CSCD
2006年第9期91-93,共3页
Computer Engineering & Science
关键词
多目标优化
遗传算法
演化算法
PARETO最优
multl-objective optimization
genetic algorithm
evolutionary algorithm
Pareto optimal
