基于免疫机制的动态约束多目标优化免疫算法  

Dynamic Constrained Multi-objective Optimization Immune Algorithm Based on Immune Mechanisms

作　　者：陈善龙[1] 张著洪[1] 

机构地区：[1]贵州大学理学院系统科学及信息技术研究所,贵阳550025

出　　处：《贵州大学学报（自然科学版）》2008年第3期262-267,共6页Journal of Guizhou University:Natural Sciences

基　　金：国家自然科学基金(60565002)

摘　　要：该文针对一类决策空间维数可变且带约束条件的动态多目标优化问题,基于生物免疫系统的机理,提出一种结构简单、易于应用的动态约束多目标优化免疫算法。算法设计中,借助抗体识别功能,设计环境识别规则,加速相似环境的寻优过程;依据约束控制概念,设计挑选较好抗体的免疫选择操作;引入基于两级概率控制方案的两种不同的变异策略,进行抗体变异。借助三种性能评价指标,通过该算法与两种出众的算法比较,数值实验结果表明此算法能够获得满意的搜索效果以及具有较强的环境跟踪能力。For a class of dynamic multi-objective optimization problems with constraints and variable dimensions of design space, a dynamic constrained multi-objective optimization immune algorithm （ DCMOIA）, of simple structure and availability, is proposed based on the metaphors of the biological immune system. In designs of the algorithm, an environmental recognition rule is developed to step up the process of optimization for similar environments in terms of the function of antibody recognition, while the concept of constrained-domination is used to design an immune selection operator to pick up better antibodies. Besides, two kinds of mutation strategies based on two-level probability control are developed to mutate the antibodies. Depending on three performance indexes proposed and two popular algorithms, comparatively numerical experiments show that DCMOIA is of satisfactory search effect and strong capability of environment tracking.

关 键 词：动态多目标优化 免疫算法 约束处理 环境跟踪 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]