An efficient subscription index for publication matching in the cloud

详细信息    查看全文

• 作者：Zongmin Cui ; ^a ; ^{cuizm01@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Zongda Wu^b ; ^{zongda1983@163.com" class="auth_mail" title="E-mail the corresponding author} ; Caixue Zhou^a ; ^{charlesjjjx@126.com" class="auth_mail" title="E-mail the corresponding author} ; Guangyong Gao^a ; ^{gaoguangyong@163.com" class="auth_mail" title="E-mail the corresponding author} ; Jing Yu^a ; ^{yujingellemma@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Zhiqiang Zhao^a ; ^{zq_zhao@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; Bin Wu^c ; ^{wubincs@gmail.com" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Publish/subscribe ; Matching ; Predicate ; Index
• 刊名：Knowledge-Based Systems
• 出版年：2016
• 出版时间：15 October 2016
• 年：2016
• 卷：110
• 期：Complete
• 页码：110-120
• 全文大小：1141 K

文摘

Publish/subscribe has been successfully used in a variety of information dissemination applications. However, in a cloud computing environment, the enormous amount of information results in a very high requirement for the computing performance of a publish/subscribe method. In this paper, we propose an efficient index called Enindex for publish/subscribe matching. First, we group all the subscriptions submitted by subscribers, based on the key attributes (i.e., the most frequent attributes occurring in the subscriptions). Second, we group all the predicates contained in the subscriptions, according to three basic operators: ≥ (greater),=(equal), and ≤ (less), so as to remove the repeated predicates, and thus reduce the memory overhead. Finally, we propose an effective index structure to combine the grouped subscriptions together with the grouped predicates. Enindex not only has a small memory overhead, but also can support efficient publish/subscribe matching and online subscription updating. We conduct extensive experiments on synthetic datasets, and the experimental results demonstrate the superiority of the Enindex over state-of-the-art methods in terms of memory overhead and computing efficiency.