MapReduce-based skyline query processing scheme using adaptive two-level grids

Skyline queries are extensively used for solving many problems such as product recommendation, because skylines contain data to satisfy various user criteria. Currently, skyline queries for large databases are being investigated. In particular, the research using the existing index techniques to MapReduce for large databases in a parallel and distributed environment has been actively conducted. A characteristic of skyline queries is that the data closer to the origin dominate more data regions. In this paper, we propose a novel index technique using adaptive two-level grids, called TLG. It separates the data space into regions by considering the characteristic of the skyline queries. We also propose an efficient skyline query algorithm based on TLG. It computes the skylines for each data region for reducing the number of checking dominance relationship between data points in different regions.