您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2009, Vol. 39 ›› Issue (5): 32-37.

• 机器学习与数据挖掘 • 上一篇    下一篇

基于结构化覆盖网的连续 top-k 联接查询算法

赵科军 王新军 刘洋 仇一泓   

  1. 赵科军,王新军:山东大学计算机科学与技术学院, 山东 济南 250101; 
    赵科军,王新军,刘洋,仇一泓:山东大学网络信息中心, 山东 济南 250100
  • 收稿日期:2008-12-18 出版日期:2009-10-16 发布日期:2009-10-16
  • 作者简介:赵科军(1981-),男,工程师,硕士研究生,研究方向为对等网计算、数据库和信息检索. E-mail: jeff@sdu.edu.cn

Algorithms of continuous top-k join query over structured overlay networks

  1.  ZHAO Ke-Jun, WANG Xin-Jun:School of Computer Science and Technology, Shandong University, Jinan 250101, China;    ZHAO Ke-Jun, WANG Xin-Jun, LIU Xiang, CHOU Yi-Hong:Network Center of Shandong University, Jinan 250100, China
  • Received:2008-12-18 Online:2009-10-16 Published:2009-10-16

摘要:

由于分布式计算环境中数据的分散性,在结构化覆盖网上进行连续查询是一个富有挑战性的工作.本文首次提出基于结构化覆盖网连续top-k联接查询的算法,在对新数据做联接查询前,通过预计算排序函数的估值,对不可能最终影响top-k结果的数据裁剪,达到减少网络流量和计算负载目的.实验证明,这种方法在保证更多的节点参与到查询同时,能有效降低网络流量.

关键词: 对等网;结构化覆盖网;连续查询;top-k

Abstract:

It is challenging to process continuous queries over structured overlay networks due to the distribution characteristic of the environment.An algorithm based on  top-k join queries over structured overlay networks is presented. In the proposed algorithms, the data that can not contribute the finale top

-k results was discarded based on the  pre-computing results of ranked functions The performance of the algorithms was analyzed. Our algorithms reduced  the network traffic  while more nodes participate in the query process.

Key words:  structured overlay network; continuous query; top-k

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!