摘要
为了在多目标演化算法解决问题时保证解集的多样性,提出了一个有效的梯度拥挤度多样性保持策略,以及基于该保持策略的多目标演化算法;设计了多样性的熵度量准则,以及多样化种群初始策略。实验证明,提出的算法在种群多样性保持方面取得了较好的效果。
An efficient method for pruning non - dominated set and a muhi - objective evolutionary algorithm were proposed in order to maintain the population diversity. The entropy metrics for testing the population diversity as well as the diversity initial population strategy were proposed . The experiment results show that the algorithm is effective in diversity maintenance.
出处
《武汉理工大学学报(信息与管理工程版)》
CAS
2008年第5期696-700,共5页
Journal of Wuhan University of Technology:Information & Management Engineering
基金
国家自然科学基金资助项目(40701153)
关键词
多目标演化算法
多样性保持策略
熵度量
muhi -objective evolutionary algorithm
diversity maintenance strategy
entropy metrics