基于Hadoop的改进遗传算法  

Improved Genetic Algorithm Based on Hadoop

作　　者：包达尔罕 

机构地区：[1]中国石油大学地球与信息学院,北京102249

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2015年第1期62-65,共4页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：内蒙古自然科学基金资助项目(2013MS0910)

摘　　要：利用Hadoop的并行式处理技术改进了遗传算法.通过将种群划分为多个子种群,并将每个子种群由一个单一的MapReduce任务来处理,实现了遗传算法的并行化.通过解决OneMax问题的一系列实验,验证了基于Hadoop的遗传算法提高了运行效率与正确性.The genetic algorithm was improved based on the parallel process technology of Hadoop. The parallel genetic algorithm is implemented through divided the population into several sub-populations and each sub-population was processed by a single MapReduce.It is tested that the genetic algorithm based on Hadoop improved the efficiency and the accuracy through solving the OneMax problem.

关 键 词：遗传算法 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]