高效处理分布式数据流上skyline持续查询算法  

Efficient Processing of Continuous Skyline Query over Distributed Data Streams

作　　者：孙圣力[1] 李金玖[1] 朱扬勇[1] 

机构地区：[1]复旦大学计算机与信息技术系,上海200433

出　　处：《软件学报》2009年第7期1839-1853,共15页Journal of Software

基　　金：国家重点基础研究发展计划(973)No.2005CB321905~~

摘　　要：基于非共享策略,围绕着降低系统反应延迟与通信负荷的目标,提出了一种分两阶段渐进求解的分布式算法BOCS(based on the change of skyline),并对算法的关键实现环节,如协调站点与远程站点间的通信、skyline增量的计算等进行了系统优化,使算法在通信负荷与反应延迟上达到了较好的综合性能.理论分析证明,在所有基于非共享策略的算法中,BOCS算法通信最优.大量的对比实验结果也表明,所提出的算法高效、稳定且具有良好的可扩展性.To reduce system delay and overall communication load, this paper proposes an efficient algorithm BOCS （based on the change of skyline） which is out of share-nothing strategy. BOCS is to solve this issue through progressive refinement by two steps. This paper provides analytical results and they show that BOCS is optimal in terms of the communication overhead among all algorithms which are out of share-nothing strategy. Theoretical analysis and extensive experiments demonstrate that these methods are efficient, stable and scalable.

关 键 词：分布式数据流 SKYLINE 持续查询 通信最优 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]