摘要
介绍多峰搜索空间的等价类模型 ,应用该模型分析确定性排挤 (DC)小生态遗传算法的遗传漂移现象。分析结果表明 ,DC的替换错误导致类形成与类维持的矛盾 ,DC不能克服类之间的遗传漂移 ,且倾向于维持高适应值的类而丢失低适应值的类。因此 ,对于复杂多峰优化问题 ,DC不能在单一种群中并行地维持多个全局或局部最优解。
Equivalence class model of multimodal search space is introduced. It is used to analyze the genetic drift in niching genetic algorithms using deterministic crowding method (DC). The results show that the replacement errors of similar individuals in DC cause the confliction between generating new classes and maintaining the existing classes, and DC is not able to remove the genetic drift in evolutionary computation, but inclined to maintain the classes with higher fitness and lose the ones with lower fitness. Thus DC is not capable of finding and maintaining multiple global or local optima in parallel in a single population when used to optimize complicated multimodal problems.
出处
《湖南理工学院学报（自然科学版）》
CAS
2004年第3期34-38,共5页
Journal of Hunan Institute of Science and Technology(Natural Sciences)
基金
国家自然科学基金项目 :编号 5 0 2 75 170
湖南省教育厅科学研究基金资助项目 :编号 2 0 0 1C3 80
2 0 0 2A0 5 2
关键词
进化算法
小生态
确定性排挤
遗传漂移
evolutionary algorithm
niche
deterministic crowding
genetic drift
