State-based Event Detection Optimization for Complex Event Processing

Abstract

Detection of patterns in high speed, large volume of event streams has been an important paradigm in many application areas of Complex Event Processing (CEP) including security monitoring, financial markets analysis and health-care monitoring. To assure real-time responsive complex pattern detection over high volume and speed event streams, efficient event detection techniques have to be designed. Unfortunately evaluation of the Nondeterministic Finite Automaton (NFA) based event detection model mainly considers single event query and its optimization. In this paper, we propose multiple event queries evaluation on event streams. In particular, we consider scalable multiple event detection model that shares NFA transfer states of different event queries. For each event query, the event query is parse into NFA and states of the NFA are partitioned into different units. With this partition, the same individual state of NFA is run on different processing nodes, providing states sharing and reducing partial matches maintenance. We compare our state-based approach with Stream-based And Shared Event processing (SASE). Our experiments demonstrate that state-based approach outperforms SASE both on CPU time usage and memory consumption.

Keywords

• Radio frequency identification (RFID)
• Complex event processing
• Data stream
• Pattern match
• Event instance
• Sensor network.