多目标扰动生物地理学优化算法  

Multi-objective disturbance biogeography-based optimization algorithm

作　　者：徐志丹[1] 莫宏伟[2] 

机构地区：[1]哈尔滨商业大学基础科学学院,哈尔滨150028 [2]哈尔滨工程大学自动化学院,哈尔滨150001

出　　处：《控制与决策》2014年第2期231-235,共5页Control and Decision

基　　金：国家自然科学基金项目(61075113);中央高校基本科研业务重大专项基金项目(HEUCFZ1209);黑龙江省杰出青年科学基金项目(JC201212);哈尔滨商业大学青年教师自然科学基金项目(HCUL2013013)

摘　　要：提出一种多目标扰动生物地理学优化算法(MDBBO)来求解多目标优化问题(MOPs).该算法基于现有群体中非支配可行解的比率,联合个体非支配等级排序和拥挤距离对个体进行评价;在生物地理迁移策略基础上提出扰动迁移算子并应用于群体进化,增强群体多样性;应用归档种群来保存所获得的非支配可行解,并用循环拥挤距离法对其更新,确保群体的均匀分布性.通过标准函数测试以及与经典算法比较表明了该算法求解MOPs的有效性.A multi-objective disturbance biogeography-based optimization algorithm（MDBBO） is proposed for multi- objective optimization problems（MOPs）. Based on the ratio of non-dominated feasible solutions in current population, individuals are evaluated by combining their non-dominated rank sorting and crowded distances. A disturbance migration operator is proposed based on the biogeography migration strategy, which is applied to the evolution of the population so that the diversity of the population can be improved. An archive population is applied to store non-dominated feasible individuals gained, while the method of circle crowded disturbance is used to update the archive population to ensure the uniform distribution of population. Simulation results on benchmark test problems show the effectiveness of the MDBBO for MOPs.

关 键 词：生物地理学优化算法 扰动迁移算子 多目标优化 PARETO最优解集 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]