PROJECT TITLE :

Efficient Processing of Skyline Queries Using MapReduce - 2017

ABSTRACT:

The skyline operator has attracted considerable attention recently because of its broad applications. But, computing a skyline is challenging nowadays since we tend to have to house big information. For information-intensive applications, the MapReduce framework has been widely used recently. In this paper, we have a tendency to propose the efficient parallel algorithm SKY-MR+ for processing skyline queries using MapReduce. We 1st build a quadtree-based mostly histogram for house partitioning by deciding whether to separate every leaf node judiciously primarily based on the advantage of splitting in terms of the estimated execution time. Likewise, we have a tendency to apply the dominance power filtering methodology to effectively prune non-skyline points in advance. We have a tendency to next partition knowledge primarily based on the regions divided by the quadtree and compute candidate skyline points for each partition using MapReduce. Finally, we check whether or not each skyline candidate purpose is really a skyline point in every partition using MapReduce. We tend to additionally develop the workload balancing ways to make the estimated execution times of all offered machines to be similar. We tend to did experiments to check SKY-MR+ with the state-of-the-art algorithms using MapReduce and confirmed the effectiveness yet as the scalability of SKY-MR+.