To Share, or not to Share Online Event Trend Aggregation Over Bursty Event Streams, 2021

ABSTRACT. Complex event processing (CEP) systems continuously evaluate large workloads of pattern queries under tight time constraints. Event trend aggregation queries with Kleene patterns are commonly used to retrieve summarized insights about the recent event trends in event streams. To reduce the processing latency of these aggregation queries, special-purpose optimization techniques, online aggregation and common sub-pattern sharing, have been introduced. However, these methods are limited due to their overhead of repetitive computations or unnecessary pattern constructions. Further, they result in statically selected and hence rigid sharing plans that are often sub-optimal under stream fluctuations. In this work, we thus propose a novel framework Hamlet that is the first to overcome these limitations. Hamlet introduces two key innovations. First, Hamlet dynamically decides whether to share or not to share event trend aggregation queries depending on the current stream properties to harvest the maximum sharing benefit. Second, Hamlet is equipped with a highly efficient shared trend aggregation execution strategy that avoids trend construction. Our experimental study on both real and synthetic data sets demonstrates that Hamlet consistently reduces query latency by up to five orders of magnitude compared to state-of-the-art approaches.