Multi-dimensional Range Query for Data Management using Bloom Filters

Providing range query as basic network services has received much research attention recently. Range query can exhibit all items located within a certain range. Previous approaches to represent and query items, such as Distributed Hash Tables (DHT) or R-tree structures, use too much storage space to store and maintain items to achieve exact query results. Corresponding structures cannot effectively support operations on items that have multi-dimensional attributes. In this paper, we propose a simple and space-efficient structure, i.e., Multi-Dimensional Segment Bloom Filter (MDSBF), to support range query for data management. Our approach logically divides the range of multi-dimensional attributes into several segments to support fast and accurate lookups. We also develop a simple algorithm to achieve load balance among multiple segments and improve query accuracy. Through theoretical analysis and performance evaluation, we demonstrate that the MDSBF structure can efficiently support range query service for items with multidimensional attributes.