We consider k-dominant skyline computation when the underlying dataset is partitioned into geographically distant computing core that are connected to the coordinator (server). The existing k-dominant skyline solutions are not suitable for our problem, because they are restricted to centralized query processors, limiting scalability and imposing a single point of failure. Moreover, k-dominant skyline computation does not follow transitivity property like skyline computation. In this paper, we developed a multicore based spatial k-dominant skyline (MSKS) computation algorithm. MSKS is a feedback-driven mechanism, where the coordinator iteratively transmits data to each computing core. Computing core is able to prune a large amount of local data, which otherwise would need to be sent to the coordinator. Furthermore, it supports a user-friendly progress indicator that allows user to modify (insert, delete, and update) and monitor the progress of long running k-dominant skyline queries. Extensive performance study shows that proposed algorithm is efficient and robust to different data distributions and achieves its progressive goal with a minimal overhead.
展开▼