一种基于支配图的多维数据流Top-k高效查询算法  

High-efficiency Top-k queries algorithm on multi-dimensional data streams based on domination graph

作　　者：刘卉[1] 曾利军[1] 黄樱[1] 

机构地区：[1]湖南工学院计算机与信息科学学院,湖南衡阳421002

出　　处：《计算机应用研究》2014年第6期1791-1794,共4页Application Research of Computers

基　　金：国家自然科学基金重点资助项目(60933009);湖南省科技计划资助项目(2013SK3177;2011FJ3108);湖南省教育厅科学研究项目(12C0655);湖南工学院院级科学研究项目(HY12008)

摘　　要：为改善传感器网络多维数据查询扩展、减少通信量及提高查询精度,提出了一种新的用户多维数据查询处理构架。该处理框架能有效实现支配图,并能根据用户偏好函数进行任意数据查询。该框架在节点通信量上提出了更新滤波器算法和节点处理抽取算法来达到减少数据通信量,在滤波器算法中利用滤波器来避免sink分发所有的RSsink数据的目的,而节点处理算法则采用自适应分发数据机制来减少数据的通信量。仿真结果表明,改进数据查询算法比中央收集算法和基本查询算法在通信量上有明显的减少。与中央处理算法相比,通信量减少了80%以上。To improve the query expansion on multi-dimensional data in sensor networks,reduce communication traffic and improve the query precision,this paper proposed a new framework of query process on user multi-dimensional data.The framework could effectively realize domination graph,which implemented data query at random according to user preference function.The framework on node communication traffic proposed update filter algorithm and node extraction algorithm in order to reduce data communication traffic,it made use of the filter to avoid sink deliver all the RSsin kdata to the filter algorithm,and the node extraction algorithm usesd an adaptive data distribution mechanism to reduce data communication traffic.The simulation results indicate that the modified data queries algorithm is a sharp fall of communication traffic than the central collection algorithm and the basic query algorithm.It compares with the central processing algorithm on communication traffic to reduce by 80% or more.

关 键 词：查询扩展 查询精度 偏好函数 滤波器 抽取算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]