SB-Qtree: Scalable spatial index for server cluster

As the mobile users increases and services area for Location-Based Services (LBSs) becomes global scale, the central LBS server suffers from processing the massive volume of spatial data and query requests. To solve this problem, a cloud computing is emerged as an alternative for LBSs and few number of researches, such as SD-Rtree, have been conducted to date. However, those researches do not solve the excessive message cost among servers and rely on the caches in mobile clients. Motivated by this issue, we propose an distributed index scheme, termed Scalable Bucket Quadtree (SB-Qtree), for accessing spatial data efficiently on cluster of servers. To handle such a scalable data and provide efficient query processing, SB-Qtree maintains the index structure balanced and provides the early termination scheme. To verify the effectiveness of the proposed SB-Qtree, we implement the proposed index scheme and analyze the experimental results in terms of the message cost and the number of node access.