多目标差分演化算法研究综述  

A Survey of Multi-objective Differential Evolution Algorithms

作　　者：敖友云[1] 迟洪钦[2] 

机构地区：[1]安庆师范学院计算机与信息学院,安徽安庆246001 [2]上海师范大学数理信息学院,上海200234

出　　处：《计算机科学与探索》2009年第3期234-246,共13页Journal of Frontiers of Computer Science and Technology

摘　　要：多目标差分演化算法是一种简单有效的演化算法,已引起学术界的广泛关注,并在许多领域得到应用。首先描述了差分演化算法的基本思想;接着分析了有代表性的多目标差分演化算法,并给出了改进多目标差分演化算法的一些措施;然后讨论了多目标差分演化算法的性能度量指标,并介绍了多目标差分演化算法的一些应用领域;最后,指出了多目标差分演化算法今后的研究方向。Multi-objective differential evolution algorithm is a simple and effective evolutionary algorithm for multiobjective optimization, which has been attracted much increasing interest from academia recently and applied to various fields successfully. Firstly, the basic idea of differential evolution is introduced, and some representative multi-objective differential evolution algorithms are analyzed. Then some effective measures are presented, which can improve the performance of multi-objective differential evolution algorithms. Thereafter, a variety of performance indices for multi-objective differential evolution algorithms are discussed and some typical applications of multi-objective differential evolution algorithms are also mentioned. Finally, some promising paths for future research in this area are pointed out.

关 键 词：多目标优化 差分演化 演化算法 PARETO前沿 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]