The R*-tree: an efficient and robust access method for points and rectangles
SIGMOD '90 Proceedings of the 1990 ACM SIGMOD international conference on Management of data
SIGMOD '92 Proceedings of the 1992 ACM SIGMOD international conference on Management of data
An Algorithm for Finding Best Matches in Logarithmic Expected Time
ACM Transactions on Mathematical Software (TOMS)
A scalable content-addressable network
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
R-trees: a dynamic index structure for spatial searching
SIGMOD '84 Proceedings of the 1984 ACM SIGMOD international conference on Management of data
Efficient Cost Models for Spatial Queries Using R-Trees
IEEE Transactions on Knowledge and Data Engineering
MapReduce: simplified data processing on large clusters
OSDI'04 Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation - Volume 6
Experiences on Processing Spatial Data with MapReduce
SSDBM 2009 Proceedings of the 21st International Conference on Scientific and Statistical Database Management
An efficient multi-dimensional index for cloud data management
Proceedings of the first international workshop on Cloud data management
Indexing multi-dimensional data in a cloud system
Proceedings of the 2010 ACM SIGMOD International Conference on Management of data
An efficient quad-tree based index structure for cloud data management
WAIM'11 Proceedings of the 12th international conference on Web-age information management
MD-HBase: A Scalable Multi-dimensional Data Infrastructure for Location Aware Services
MDM '11 Proceedings of the 2011 IEEE 12th International Conference on Mobile Data Management - Volume 01
Hi-index | 0.00 |
With the advent of the era for big data, demands of various applications equipped with distributed multi-dimensional indexes become increasingly significant and indispensable. To cope with growing demands, numerous researchers demonstrate interests in this domain. Obviously, designing an efficient, scalable and flexible distributed multi-dimensional index has been confronted with new challenges. Therefore, we present a brand-new distributed multi-dimensional index method--EDMI. In detail, EDMI has two layers: the global layer employs K-d tree to partition entire space into many subspaces and the local layer contains a group of Z-order prefix R-trees related to one subspace respectively. Z-order prefix R-Tree (ZPR-tree) is a new variant of R-tree leveraging Z-order prefix to avoid the overlap of MBRs for R-tree nodes with multi-dimensional point data. In addition, ZPR-tree has the equivalent construction speed of Packed R-trees and obtains better query performance than other Packed R-trees and R*-tree. EDMI efficiently supports many kinds of multi-dimensional queries. We experimentally evaluated prototype implementation for EDMI based on HBase. Experimental results reveal that EDMI has better performance on point, range and KNN query than state-of-art indexing techniques based on HBase. Moreover, we verify that Z-order prefix R-Tree gets better overall performance than other R-Tree variants through further experiments. In general, EDMI serves as an efficient, scalable and flexible distributed multi-dimensional index framework.