基于合作模型的协同免疫多目标优化算法  

A Cooperative Immune Coevolutionary Algorithm for Multi-Objective Optimization

作　　者：戚玉涛[1,2] 刘芳[1,2] 任元[1] 刘静乐[1] 焦李成[2] 

机构地区：[1]西安电子科技大学计算机学院,陕西西安710071 [2]西安电子科技大学智能感知与图像理解教育部重点实验室,陕西西安710071

出　　处：《电子学报》2014年第5期858-867,共10页Acta Electronica Sinica

基　　金：国家教育部博士点基金(No.20090203120016;No.20100203120008);中国博士后科学基金(No.20090461283;No.20090451369;No.201104658);陕西省自然科学基础研究计划(No.2011JQ8010);中央高校基本科研业务费专项资金(No.K5051203007;No.K5051203002;No.K5051302023);国家自然科学基金(No.61272279);新世纪支持计划(No.NCET-12-0920);国家重点基础研究发展计划(No.2013CB329402);高等学校学科创新引智计划(No.B07048);教育部长江学者和创新团队发展计划(No.IRT1170)

摘　　要：本文针对多目标优化问题Pareto最优解集合(PS)的分布特点,构造了一种基于新的子任务划分方法的合作型协同进化模型,并将该模型引入人工免疫系统中,提出了一种基于合作模型的协同免疫多目标优化算法(A Cooperative Immune Coevolutionary Algorithm for Multiobjective Optimization,CICAMO).CICAMO算法运用Tchebycheff分解方法进行子种群划分,然后对各个子种群建立线性概率统计模型分段逼近整个PS,在抗体繁殖上结合了克隆选择和模型采样两种方式.实验结果表明,CICAMO算法在求解质量和收敛速度上均表现良好,尤其对于决策变量非线性相关的多目标优化问题,性能尤为突出.According to the distribution characteristics of the Pareto set （PS） of multi-objective optimization problems （MOPs）, a cooperative coevolutionary model with new problem decomposition method was designed. By introducing the proposed coevolutiunary model into artificial immune system, a cooperative immune coevolutionary algorithm for multi-objective optimization （CICAMO） was proposed.In CICAMO,the Tchebycheff decomposition method is employed to divide sub-populations at first, and then linear probabilistic models are built for each sub-population to piecewise approximate the distribution of the whole PS. In anti- body reproducing step, two types of approaches based on clonal selection and model sampling are employed. Experimental results in- dicate that CICAMO can achieve a good performance in terms of both solution quality and convergence rate, especially when solving MOPs with non-linear relationship between decision variables.

关 键 词：多目标优化 人工免疫算法 协同进化 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]