文章基本信息

标题：STLIS: A Scalable Two-Level Index Scheme for Big Data in IoT
本地全文：下载
作者：Yonglin Leng ; Zhikui Chen ; Yueming Hu 等
期刊名称：Mobile Information Systems
印刷版ISSN：1574-017X
出版年度：2016
卷号：2016
DOI：10.1155/2016/5341797
出版社：Hindawi Publishing Corporation
摘要：The rapid development of the Internet of Things causes the dramatic growth of data, which poses an important challenge on the storage and quick retrieval of big data. As an effective representation model, RDF receives the most attention. More and more storage and index schemes have been developed for RDF model. For the large-scale RDF data, most of them suffer from a large number of self-joins, high storage cost, and many intermediate results. In this paper, we propose a scalable two-level index scheme (STLIS) for RDF data. In the first level, we devise a compressed path template tree (CPTT) index based on S-tree to retrieve the candidate sets of full path. In the second level, we create a hierarchical edge index (HEI) and a node-predicate (NP) index to accelerate the match. Extensive experiments are executed on two representative RDF benchmarks and one real RDF dataset in IoT by comparison with three representative index schemes, that is, RDF-3X, Bitmat, and TripleBit. Results demonstrate that our proposed scheme can respond to the complex query in real time and save much storage space compared with RDF-3X and Bitmat.