Efficient processing of top-k dominating queries in distributed environments

摘要: Due to the recent massive data generation, preference queries are becoming an increasingly important for users because such retrieve only a small number of preferable objects from huge multi-dimensional dataset. A top-k dominating query, which retrieves k highest in given dataset, is particularly supporting multi-criteria decision making this query can find interesting intuitive way exploiting advantages and skyline queries. Although efficient algorithms have been studied over centralized databases, there no studies deal with distributed environments. The management distributed, so it necessary support processing In paper, we address, first time, challenging problem networks propose method retrieval, avoids redundant communication cost latency. Furthermore, also approximate version our proposed method, further reduces cost. Extensive experiments on both synthetic real demonstrated efficiency effectiveness methods.