Article in Proceedings INPROC-2014-31

BibliographyOttenwälder, Beate; Koldehofe, Boris; Rothermel, Kurt; Hong, Kirak; Ramachandran, Umakishore: RECEP: Selection-based Reuse for Distributed Complex Event Processing.
In: Proceedings of the 8th ACM International Conference on Distributed Event-Based Systems (DEBS 2014).
University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology.
pp. 59-70, english.
ACM, May 2014.
DOI: 10.1145/2611286.2611297.
Article in Proceedings (Conference Paper).
CR-SchemaC.2.1 (Network Architecture and Design)
C.2.4 (Distributed Systems)
Keywordsmobility; complex event processing; query optimization

An appealing use case of complex event processing (CEP) systems is for mobile users to react in real-time to events in their environment, e.g., to the occurrence of a dangerous situation such as an accident. Maintaining mobile CEP systems is highly resource intensive since in many cases events need to be detected in a consumer-centric manner to ensure low latency event detection and high quality of results. In this paper we propose the RECEP system to increase the scalability of mobile CEP systems. In the presence of mobile users with partially overlapping interest, the RECEP system offers methods to efficiently reuse computations and this way reduces the resource requirements of mobile CEP. Since reuse of computations happens with respect to well defined quality metrics, RECEP can be easily tailored to specific mobile applications and maximize the resource savings for their desired quality in terms of precision and recall of the processed events from the user's environment.

Full text and
other links
PDF (415332 Bytes)
Copyright© ACM, 2014. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proc. 8th ACM International Conference on Distributed Event-Based Systems (DEBS '14).
Department(s)University of Stuttgart, Institute of Parallel and Distributed Systems, Distributed Systems
Entry dateMay 5, 2014
   Publ. Department   Publ. Institute   Publ. Computer Science