DLACEP: A Deep-Learning Based Framework for Approximate Complex Event Processing
Authors
Adar Amir, Technion, Israel Institute of Technology, Haifa, Israel; Ilya Kolchinsky, Red Hat and Technion, Israel Institute of Technology, Haifa, Israel; and Assaf Schuster, Technion, Israel Institute of Technology, Haifa, Israel
Abstract
Complex event processing (CEP) is employed to detect user-specified patterns of events in data streams. CEP mechanisms operate by maintaining all sets of events that can potentially be composed into a pattern match. This approach can be wasteful when many of the sets do not participate in an actual match and are therefore discarded.
We present DLACEP, a novel framework that fuses deep learning with CEP to efficiently extract complex pattern matches from streams. To the best of our knowledge, this is the first time deep learning is employed to detect events constituting a pattern match in the realm of CEP. To assess our approach, we performed extensive empirical testing on various scenarios with both real-world and synthetic data. We showcase examples in which our method achieves an increase in throughput of up to three orders of magnitude compared to solely employing CEP, while only suffering a minor loss in the number of detected matches.
From
SIGMOD ’22: Proceedings of the 2022 International Conference on Management of Data, June 2022, Pages 340–354, https://doi.org/10.1145/3514221.3526136