A High Throughput Complex Event Detection Technique with Bulk Evaluation
Naotaka Nishimura, Hideyuki Kawashima, Hiroyuki Kitagawa · 2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing · 2013
Complex event processing (CEP) queries are important to detect valuable patterns from event streams. This paper proposes a high throughput query evaluation technique for CEP queries. Key concept is link aggregation in active instance stacks. Using aggregated links, our proposal evaluates multiple events in a bulk so that sequence construction process runs less frequently than conventional technique proposed in SASE. It reduces traversals for the same links. Consequently, our proposal improves throughput. We conducted an experiment to compare proposal and conventional one. The result of experiment showed that our proposal showed 5.24 times higher throughput than SASE at the maximum case.