CAJ | 학술논문

由于我国电网发展迅速、日趋壮大、大量新设备投入使用，需要对海量的设备状态数据和动态信息进行在线收集并在指定的时间内完成处理，这就对海量数据储存与处理提出了更高的要求、带来了严峻的挑战。为了处理这些海量数据设计并实现了基于Hadoop技术的数据储存处理系统，包括Hadoop集群、HBase、集群管理客户端。通过基准测试、IO处理性能验证和查询性能分析，验证了该系统具有分布式海量储存及高效查询的优势，适合电网大数据的储存与处理。
유우아국전망발전신속、일추장대、대량신설비투입사용，수요대해량적설비상태수거화동태신식진행재선수집병재지정적시간내완성처리，저취대해량수거저존여처리제출료경고적요구、대래료엄준적도전。위료처리저사해량수거설계병실현료기우Hadoop기술적수거저존처리계통，포괄Hadoop집군、HBase、집군관리객호단。통과기준측시、IO처이성능험증화사순성능분석，험증료해계통구유분포식해량저존급고효사순적우세，괄합전망대수거적저존여처리。
Due to The State Grid has developed rapidly,growing with each passing day,a lot of new equipment put into use,the need for huge amounts of equipment status data and online dynamic information collection and processing within a specified time,it is of huge amounts of data storage and processing put forward higher request,has brought serious challenges.In order to deal with the huge amounts of data was designed and implemented based on the technology of Hadoop data storage processing system,including Hadoop,HBase, Cluster management client.Through benchmark testing,IO performance verification processing and query performance analysis,verified the system has the advantages of the distributed mass storage and efficient query is suitable for large data storage and processing of the grid.