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.
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.
出处
《山东大学学报(工学版)》
CAS
北大核心
2009年第5期32-37,57,共7页
Journal of Shandong University(Engineering Science)