摘要
提出一种基于数据场的多目标引力搜索算法(DFMOGSA).该算法利用外部档案存储非支配解,同时将外部档案视为目标空间的数据场,通过计算非支配解的势能来判断每个解的密度;密度最低的解被选为第1类引导粒子,直接吸引粒子向低密度区域收敛,提高解分布的均匀性;另外,为了确保算法收敛在种群内,选择较优粒子作为第2类引导粒子,通过引力引导粒子搜索.对比实验结果表明了DFMOGSA算法的有效性和优越性.
A multi-objective gravitational search algorithm（GSA） based on data field（DFMOGSA） is proposed, in which the external archive is applied to store the obtained non-dominated solutions, and is mapped into a data field in the objective space. Accordingly, each non-dominated solution is assigned a density value based on its potential energy. The solution with the smallest density value is chosen as the first kind of guide-particle. This guide-particle directly leads population particles convergence towards the low density region, and thus improves the solution distribution. Moreover, several superior population particles are selected as the second kind of guide-particles. These guide-particles direct each of the population particles fully explore the feasible search space through their resultant gravitational force, which ensures the convergence performance. Simulation results on benchmark test problems show the effectiveness and superiority of the DFMOGSA for multi-objective optimization problems（MOPs）.
出处
《控制与决策》
EI
CSCD
北大核心
2017年第1期47-54,共8页
Control and Decision
基金
国家自然科学基金项目(41471353)
中央高校基本科研业务费专项资金项目(14CX02039A
15CX06001A)
海洋公益性行业科研专项项目(201405028)
关键词
数据场
引力搜索算法
多目标优化
密度
引导粒子
data field
gravitational search algorithm
multi-objective optimization
density
guide-particle
