Reliable speculative processing of out-of-order event streams in generic publish/subscribe middlewares
Complex Event Processing
Event monitoring
Stream Processing
DOI:
10.1145/2488222.2488263
Publication Date:
2013-07-02T14:33:48Z
AUTHORS (2)
ABSTRACT
In surveillance, sports, finances, etc., distributed event-based systems are used to detect meaningful events with low latency in high data rate event streams. Both known approaches deal the predominant out-of-order arrival at detectors have their shortcomings: buffering introduce latencies for ordering and stream revision may result system overloads due unbounded retraction cascades. This paper presents a speculative processing technique streams that enhances typical approaches. contrast other our novel encapsulates detector, uses delay but also speculatively processes portion of it, adapts degree speculation runtime fit available resources so detection becomes minimal.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (28)
CITATIONS (14)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....