Towards Efficient Dissemination of Linked Data in the Internet of Things
Yongrui Qin, Quan Z. Sheng, Nickolas Falkner, Ali Shemshadi, Edward Curry · 2014
The Internet of Things (IoT) envisions smart objects collecting and sharing data at a global scale via the Internet. One challenging issue is how to disseminate data to relevant data consumers efficiently. In this paper, we leverage semantic technologies which can facilitate machine-to-machine communications, such as Linked Data, to build an efficient information dissemination system for semantic IoT. The system integrates Linked Data streams generated from various data collectors and disseminates matched data to relevant data consumers based on Basic Graph Patterns (BGPs) registered in the system by those consumers. To efficiently match BGPs against Linked Data streams, we introduce two types of matching, namely semantic matching and pattern matching, by considering whether the matching process supports semantic relatedness computation. Two new data structures, namely MVR-tree and TP-automata, are introduced to suit these types of matching respectively. Experiments show that an MVR-tree designed for semantic matching can achieve a twofold increase in throughput compared with the naive R-tree based method. TP-automata, as the first approach designed for pattern matching over Linked Data streams, also provides two to three orders of magnitude improvements on throughput compared with semantic matching approaches.