etalis_debs_2010
DESCRIPTION
Pattern matching against event streams is a new paradigm of processing continuously arriving events with the goal of identifying meaningful patterns (complex events). An issue arises when some events get delayed due to, e.g., network latencies or sensor and machine failures. In this work we propose a novel technique for processing out-of-order events without artificial delays. We present the design of an out-of-order event processor, and a general low-level garbage collector; both implemented in ETALIS system.TRANSCRIPT
Processing Out-Of-Order Event Streams in ETALIS
Paul Fodor, Darko Anicic, Sebastian Rudolph, Roland Stühmer4th ACM International Conference on Distributed Event-Based Systems (DEBS 2010), Cambridge, UK
Event Processing in ETALIS
Figure source: Tali Yatzkar & Opher Etzion, IBM Research
Knowledge-based EP
What are semantic relations between events w.r.t background knowledge?
ψ = ? π ← φ ∨ ¬ ψ. φ = true.
EP with on-the-fly knowledge evaluation and stream reasoning:
• Classification and filtering
• Context
• Intelligent recommendation
• predictive analysis
Out-of-Order Event Processing
Hedge fund with independent cooperating agents: events arrive out-of-order.
ce1 ← stock(Agent1, “GO”, Pr1,Vol1) SEQ stock(Agent2, “GO”, Pr2,Vol2) WHERE Pr1*1.20<Pr2.ce2 ← stock(Agent1, “MS”, Pr1,Vol1) SEQ stock(Agent2, “MS”, Pr2,Vol2) WHERE Pr1>1.20*Pr2.
Missing complex events due to out-of-order stream: stock(agent1, “GO”, 100,10) SEQ stock(agent2, “GO”, 125,10);
False positives complex event ce2 due to an out-of-order event.
Inference Rule Transformation
Performance Evaluation
Configuration: Pentium dual-core processor 2GHz CPU, 3GB running on Ubuntu Linux. ETALIS was run using Yap Prolog version 5.1.31.
The execution time for in-order vs. out-of-order experiments
Thank you! Questions…
ETALIS
Open source:
http://code.google.com/p/etalis
See also our Live DEMO at:
http://krake26.perimeter.fzi.de:8080/etalis