2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS) (2015)
Dec. 11, 2015 to Dec. 13, 2015
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/DSDIS.2015.54
Complex event processing has been widely adopted in different domains, from large-scale sensor networks, smart home, trans-portation, to industrial monitoring, providing the ability of intelligent procession and decision making supporting. In many application scenarios, a lot of complex events are long-term, which takes a long time to happen. Processing long-term complex event with traditional approaches usually leads to the increase of runtime states and therefore impact the processing performance. Hence, it requires an efficient long-term event processing approach and intermediate results storage/query policy to solve this type of problems. In this paper, we propose an event processing system, LTCEP, for long-term event. In LTCEP, we leverage the semantic constraints calculus to split a long-term event into two parts, online detection and event buffering respectively. A long-term query mechanism and event buffering structure are established to optimize the fast response ability and processing performance. Experiments prove that, for long-term event processing, LTCEP model can effectively reduce the redundant runtime state, which provides a higher response performance and system throughput comparing to other selected benchmarks.
Semantics, Ontologies, Calculus, Event detection, Rail transportation, Monitoring, Control systems
M. Ma, P. Wang and C. Chu, "LTCEP: Efficient Long-Term Event Processing for Internet of Things Data Streams," 2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS), Sydney, Australia, 2015, pp. 548-555.