海量遥感数据分布式集群化存储技术研究

Research on Distributed Clustering Storage Technology for Massive Remote Sensing Data

针对当前高分辨率遥感数据的高效存储与高速访问迫切需求,采用分布式架构、对象存储和集群技术,结合遥感数据的空间特性,构建了基于数据对象的存储组织模型,设计了全分布式的存储管理架构;形成了逻辑上全球覆盖,物理上分散存储,全球遥感数据存储视图一体化,数据高效共享的分布式集群化遥感大数据存储体系。通过使用此架构,可实现遥感数据资源配置的灵活化,业务区域化特征的定制化与个性化,以及管理系统的智能化。

For the urgent needs of the high-resolution earth observation remote sensing data storage and the highspeed access,this paper uses the distributed architecture,object storage and clustering technology,combines the spatial characteristics of remote sensing data to build organizational model based on the data object,designs a storage management architecture with the spatial position as the leading.A remote sensing big data storage system with efficient sharing of distributed cluster can be reformed,that is a global coverage in logic,a dispersed storage in physics and an integration of the storage views of global data.By this architecture,the flexibility of remote sensing data resources configuration,the customization and personalization of business regionalization,and the intelligence of management systems can be achieved.