一种改进的小生境遗传算法在多目标优化中的应用  

APPLYING IMPROVED NICHE GENERIC ALGORITHM TO THE MULTI-OBJECTIVE OPTIMIZATION

作　　者：凌志钧[1] 王小平[1] 薛小平[2] 

机构地区：[1]同济大学计算机科学与工程系,上海200092 [2]同济大学信息与通信工程系,上海200092

出　　处：《计算机应用与软件》2008年第11期16-19,共4页Computer Applications and Software

基　　金：国家自然基金资助(60475019)

摘　　要：引入个体迁徙和捕猎行为的模拟,改进小生境遗传算法的思想,以加快Pareto最优解的收敛速度和保证解的多样性,使得改进的算法更适合于多目标优化求解。计算实例表明,与SPEA算法相比,所提出的算法更优越。The paper introduces the idea of simulating the activities of individual migration and predation to improve the niche genetic algo- rithm so as to accelerate the convergence speed of the Pareto-optimal set as well as to maintain the diversity of the solutions, the improved algorithm is more suitable to solve the multi-objective optimization problem. The computation instance shows that compared with the SPEA algorithm,the algorithm proposed in this paper is superior to some extents.

关 键 词：多目标优化 遗传算法 捕猎者 PARETO最优解 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] N941.5[自动化与计算机技术—计算机科学与技术]