虚拟数据代理云模型构建及数据布局

Cloud model construction of virtual data agent and data placement

综合考虑数据集间的依赖关系以及数据中心的存储容量,引入一种名为"虚拟数据代理"的新实体,通过建立虚拟数据代理云模型,将数据布局问题转换为2个映射过程,即从数据集到虚拟数据代理的映射以及从虚拟数据代理到数据中心的映射,进而提出一种基于虚拟数据代理的云模型数据布局策略(CDPVDA)。仿真实验结果表明:CDPVDA与典型的数据放置策略相比,可以将数据中心之间的数据传输开销降低5%～20%。

Considering the dependence between data sets and the storage capacity of data centers,a new type of entity called virtual data agent was introduced.The data placement problem was converted into two mapping processes namely mapping from the data set to the virtual data agent and mapping from the virtual data agent to the data center.Cloud model based data placement algorithm with virtual data agent(CDPVDA)was proposed.The results of simulation experiment show that compared with two typical data placement strategies,CDPVDA can reduce data transmission overhead between data centers by 5%to 20%.