基于区域分解的CRS算法  

CRS Algorithm Based on Domain Decomposition

作　　者：钱伟懿[1] 汤丹[1] 

机构地区：[1]渤海大学数学系,辽宁锦州121000

出　　处：《运筹与管理》2008年第6期11-15,共5页Operations Research and Management Science

基　　金：国家自然科学基金资助项目(10471014)

摘　　要：本文针对带有盒子约束的非线性规划问题提出一种算法,该算法把解空间分成几个区域,根据每个区域上解的信息定义其选择概率,再根据轮盘赌选择法选择某个区域,在选择的区域上进行CRS(Control Random Search)算法操作。该方法能够缩小搜索空间,从而提高算法的搜索能力及算法的收敛速度,特别是在算法的后期效果更加明显。最后把提出的算法应用到两个典型的函数优化问题中,数值结果表明,算法是可行的、有效的。In this paper, a new algorithm is proposed for the nonlinear programming problems with the box constraints. The algorithm divides the solution space into several regions. We define the selected probability according to information of solutions on each region. The CRS algorithm is used on one region which is selected based on roulette wheel selection. The method can reduce the search space. Thus, search ability and convergence rate of the algorithm can be improved. Especially, the effect is more obvious in later period of the algorithm. Finally, the proposed algorithm is applied to two typical function optimization problems, and the numerical results illustrate the accuracy and efficiency of the algorithm.

关 键 词：运筹学 CRS算法 轮盘赌选择 区域分解 全局优化 

分 类 号：O221.2[理学—运筹学与控制论]