基于免疫优化策略的副本放置算法  

Data Replica Placement Algorithm Based on Immune Optimization Strategy

作　　者：罗四维[1] 侯孟书[1] 牛新征[1] 吕孟婕 

机构地区：[1]电子科技大学计算机科学与工程学院,成都611731 [2]中国民航总局第二研究所,成都610000

出　　处：《电子科技大学学报》2017年第5期741-746,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金面上项目(61472067;61300192);国家科技支撑计划(2013BAH33F02);四川省科技计划项目(2013GZ0006);中央高校基本科研业务费(ZYGX2014J052)

摘　　要：副本放置问题在云计算环境分布式存储系统中是一个关键问题。针对现有副本放置算法存在的数据副本访问开销较大,节点负载不均衡的问题,提出了一种基于免疫优化策略的副本放置算法。通过计算节点的亲和度,并借助免疫优化系统特有的克隆选择和免疫记忆机制,对副本节点的评价和选择更加合理。基于Matlab的仿真实验证实该算法能够降低分布式存储系统的副本访问开销,均衡节点负载。The problem of replica placement is a key issue of distributed storage systems in cloud computing. Aiming at the uneven load among nodes and the high costs of replicas access, we propose a novel replica placement algorithm based on the immune optimization strategy. Through the computation of affinity of nodes, and with the help of clonal selection and immune memory mechanisms, the proposed algorithm can comprehensively evaluate and select the nodes for replica placement. Several simulations and conducted based on Matlab, and the results show that the algorithmpresented is able to reduce the cost of replica access, and makes the load between nodes more balanced.

关 键 词：云计算 分布式存储 免疫优化策略 副本放置 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]