基于访问趋势预测的时间序列数据库缓存管理研究  

Research on Time Series Database Cache Management Based on Access Trend Prediction

作　　者：艾文凯 江伟 徐丹[1] 高红亮[2] 何宇斌 AI Wenkai;JIANG Wei;XU Dan;GAO Hongliang;HE Yubin(NR Electric Co.,Ltd.,Nanjing 211102,China;CSG Power Dispatching Control Center,Guangzhou 510530,China)

机构地区：[1]南京南瑞继保电气有限公司,江苏南京211102 [2]中国南方电网电力调度控制中心,广东广州510530

出　　处：《电工技术》2022年第6期149-150,153,共3页Electric Engineering

摘　　要：针对短时间内突发访问大量时间序列数据,查询效率低的难题,提供基于访问趋势预测的时间序列数据库缓存管理方法,在常规数据库提供数据访问缓存的基础上,建立时间序列数据库双缓存机制;在常规缓存之外增加一块预测数据缓存,用于预测访问数据的预加载,以便在数据访问前将其载入内存,加快查询速度。时间序列数据库数据缓存管理方法通过对近期访问数据进行分析,预测数据访问趋势,再对预测数据进行加载,从而提高时间序列数据库数据查询效率。To the problem of low efficiency in querying a large number of time series data for sudden access in a short period of time,a time series database cache management method based on access trend prediction is proposed.On the basis of data access cache provided by conventional databases,a time series database double cache mechanism is established.In addition to the conventional cache,a predictive data cache is added to predict the pre-loading of the accessed data,so that it can be loaded into the memory before the data is accessed to speed up the query speed.The time series database data cache management method analyzes the recently accessed data,predicts the data access trend,and then loads the forecast data to the forecast cache to improve the query efficiency of the time series database data.

关 键 词：时间序列数据库缓存管理 双缓存 预测数据缓存 访问趋势 查询效率 

分 类 号：TM732[电气工程—电力系统及自动化]