时序数据多维聚合查询服务的实现  

Implementation of multidimensional aggregate query service for time series data

作　　者：盛家 房俊[1,2] 郭晓乾 王承栋 SHENG Jia;FANG Jun;GUO Xiaoqian;WANG Chengdong(Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data,North China University of Technology,Beijing 100144,P.R.China;Institute of Data Engineering,North China University of Technology,Beijing 100144,P.R.China)

机构地区：[1]北方工业大学大规模流数据集成与分析技术北京市重点实验室,北京100144 [2]北方工业大学数据工程研究院,北京100144

出　　处：《重庆大学学报（自然科学版）》2020年第7期121-128,共8页Journal of Chongqing University

基　　金：国家自然科学基金面上资助项目(61672042)。

摘　　要：随着电能质量监测点不断扩大,产生海量具有时序特性的多维电能质量数据,当前的诸多数据查询方法不能适应电网电能质量监测数据的交互式多维聚合查询需求。研究提出时序数据多维聚合服务的实现方法,为内存中预聚合后的任务结果建立哈希存储结构,对实时数据建立位图索引存储结构,将历史数据的预聚合数据尽量存储于内存中,改进随机读写的低性能问题,提升查询效率,解决交互式查询问题。同时运用最优聚合任务算法选择出尽量多的预聚合任务数,提高交互式查询命中率。实验验证了该算法的可行性,与分组二维背包算法相比,在预聚合任务数量选择方面具有一定优势。With the continuous expansion of power quality monitoring points,a large number of multi-dimensional power quality data with time series characteristics have been generated.The existing data query methods can not meet the need of interactive multi-dimensional aggregation query of power quality monitoring data.This paper presents a method to implement multi-dimensional aggregation service for sequential data.It establishes a hash storage structure for pre-aggregated task results in memory,a bitmap index storage structure for real-time data,and stores pre-aggregated historical data in memory as much as possible thereby improving the performance of random reading and writing,and the efficiency of query,solving the problem of interactive query.At the same time,the optimal aggregation task selection algorithm is used to select as many pre-aggregation tasks as possible to improve the hit rate of interactive queries.Experiments verify the feasibility of the proposed algorithm.Compared with the grouped two-dimensional knapsack algorithm,it has certain advantages in the number of pre-aggregated tasks.

关 键 词：时序数据 聚合查询 预聚合 交互式查询 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]