基于Hadoop的电力地理信息系统数据管理

Data management based on Hadoop for power geographic information system

针对传统电力地理信息系统(GIS)在存储能力、分析能力和扩展能力上的不足,将云计算技术应用到电力GIS领域,提出利用Hadoop云平台对电力GIS数据进行高效存储和管理的方案。首先对电力GIS各类数据的特点进行了分析,提出了关系型数据库与非关系型数据库相结合的数据存储策略,并在此基础上设计了基于Hadoop的电力GIS数据管理整体架构、相应的数据模型以及基于MapReduce的数据并行查询分析方法。最后,在单机和集群的环境下,对空间分析与运行数据查询的性能进行了对比与验证。实验结果表明,在数据量达到一定规模时,该方案优势明显,数据分析与查询的平均时间缩短30%以上,具有较高的效率和良好的扩展性。

In consideration of the problem that the traditional power Geographic Information System （GIS） has inabilities in storage, computing and scalability, cloud computing was applied into the power GIS field and a solution which used Hadoop cloud platform to store and manage the massive GIS data was proposed. After analyzing the characteristics of the power GIS data, a data storage strategy was proposed which combined relational database with non-relational database. Based on this strategy, the architecture of power GIS management based on Hadoop was presented, the data model and parallel data analysis based on MapReduce were designed. Finally, a quantity of experiments were carried out including spatial analysis and operation data queries in single-machine and cluster environment to compare and validate the performance. The experimental results show that the average time of data analysis and query declines over 30% after reaching certain amount of data. The proposed scheme has more obvious advantages to deal with large-scale data and has high efficiency and good feasibility.