基于多属性最优化的海洋监测数据副本布局策略  

Marine Monitoring Data Replica Layout Strategy Based on Multiple Attribute Optimization

作　　者：黄冬梅[1] 杜艳玲[1,2] 贺琪 随宏运[1] 李瑶[1] HUANG Dong-mei;DU Yan-ling;HE Qi;SUI Hong-yun;LI Yao(College of Information Technology,Shanghai Ocean Universit;East China Sea Marine Forecast Center of State Oceanic Administratio)

机构地区：[1]上海海洋大学信息学院,上海201306 [2]国家海洋局东海预报中心,上海200136

出　　处：《计算机科学》2018年第6期72-75,104,共5页Computer Science

基　　金：国家自然科学基金(41671431);国家重点研发计划(2016YFC1401907);上海市科委能力建设项目(15590501900)资助

摘　　要：数据的完整性和可靠性是保证其能被高效访问的关键,尤其是在云存储环境中,数据副本策略是影响系统性能和保障数据可用性的核心。从数据副本布局的角度,提出了基于多属性最优化的数据副本布局策略(Data Replica Layout Strategy based on Multiple Attribute Optimization,MAO-DRLS)。该策略根据数据的访问热度和存储节点的关键属性特点,为每个数据设置动态的副本数,并选择合适的节点对副本进行布局。实验表明,MAO-DRLS策略能够有效地提升数据副本的利用率,缩短系统的响应时间。The integrity and reliability of data are the key to ensure its efficient access.Especially in the cloud storage environment,data replication strategy is the core of the system performance and the availability of data.For a data replica layout,this paper put forward a data replica layout strategy based on multiple attribute optimization（MAO-DRLS）.According to the heat of data access and the key attributes of storage node,it sets the number of replicas for each dynamic data,and chooses the appropriate node to distribute the replicas.The experiments show that the MAO-DRLS strategy can effectively improve the utilization rate of data replicas and shorten the system response time.

关 键 词：海洋监测数据 数据副本 多属性最优化 数据布局 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]