Research on Performance Measures of Multi-objective Optimization Evolutionary Algorithms

摘要：

A large number of multi-objective optimizationevolutionary algorithms(MOEAs)have been developedin the past two decades.To compare these methodsrigorously,or to measure the performance of aparticular MOEA quantitatively,a variety ofperformance measures have been proposed.In thispaper,some existing widely-used performancemeasures are briefly reviewed and comparedaccording different properties.Two new performancemeasures computing the convergence towards thePareto front and the solution diversity on the Paretofront are proposed.And an outlook on how to furtherdeepen insight in performance measures of MOEAs isgiven.

作者: Zhang Lili Zeng Wenhua

作者单位: Department of Computer Science,Xiamen University,Xiamen,361005,China Software School,Xiamen University,Xiamen,361005,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 502-507

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）