| 引用本文: | 宋亚奇,刘树仁,朱永利,王德文,李 莉.电力设备状态高速采样数据的云存储技术研究[J].电力自动化设备,2013,33(10): |
| SONG Yaqi,LIU Shuren,ZHU Yongli,WANG Dewen,LI Li.Cloud storage of power equipment state data sampled with high speed[J].Electric Power Automation Equipment,2013,33(10): |
|
| 摘要: |
| 提出基于Hadoop和HBase的电力设备状态高速采样数据的存储方案，基于MapReduce设计实现了设备状态高速采样数据的并行查询方法。创建了1个包含20个节点（每个节点配置4核CPU）的Hadoop集群，并对集群进行了基准测试，测试结果表明所建集群适合进行大量数据的读写。以绝缘子泄漏电流数据为例，使用YCSB对所建存储系统进行了性能测试，测试结果表明，Hadoop和Hbase在存储容量、吞吐量以及查询延迟上提供了足够高的性能，能够满足智能电网状态监测数据可靠性及实时性要求。 |
| 关键词: 电力设备 监测 采样 数据处理 云计算 Hadoop Hbase |
| DOI： |
| 分类号: |
| 基金项目:国家自然科学基金资助项目（61074078）；新能源电力系统国家重点实验室资助项目；中央高校基本科研业务费专项资金资助项目（13MS88） |
|
| Cloud storage of power equipment state data sampled with high speed |
|
SONG Yaqi1, LIU Shuren1, ZHU Yongli1,2, WANG Dewen1, LI Li1
|
|
1.School of Control and Computer Engineering，North China Electric Power University，Baoding 071003，China;2.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources，
North China Electric Power University，Beijing 102206，China
|
| Abstract: |
| A storage scheme based on Hadoop and HBase is proposed for the power equipment state data sampled with high speed. An approach is designed and implemented based on MapReduce to query in parallel the sampled data. A Hadoop cluster containing 20 nodes，each equipped with a 4-core CPU，is created and benchmarked. Results show it is suitable for massive data reading／writing. A storage system is built for the insulator leakage current data as an example and tested by YCSB，results indicate that，Hadoop and Hbase provide sufficiently high performance in storage capacity，throughput and latency，meeting the requirements of smart grid for the reliability and real-time performance of state monitoring data. |
| Key words: power equipment monitoring sampling data processing cloud computing Hadoop Hbase |
