PLR: A Benchmark for Probabilistic Data Stream Management Systems

摘要: Inherent imprecision of data streams in many applications leads to need for real-time uncertainty management. The new emerging Probabilistic Data Stream Management Systems (PDSMSs) are being developed handle uncertainties real-time. Many approaches have been proposed so far but there is no way compare them regarding precision and efficiency. This problem motivated us design an evaluation framework performance accuracy PDSMSs with each other also probabilistic databases. In this paper, after a brief introduction PDSMSs, we describe requirements challenges designing PDSMS benchmark. Then, present different parts our including stream generator, queries, result evaluator. Furthermore, focus on implementation aspects use evaluate effects floating prototype.