Efficient Strategy for Out-of-Order Event Stream Processing

Complex event processing has been widely used in many modern applications. A key aspect of complex event processing is to extract patterns from event streams to make informed decisions in real-time. However, network latencies and machine failures may cause events to arrive out-of-order at the event processing engine. To address the problem, a number of disordered event processing techniques are proposed. In this paper, we introduce latency distance and purging time to process out-of-order event streams in real-time. Further, we present a redo strategy based on playback, with which those false pattern matches produced at the early phase can be corrected by the aid of the cloud platform. We conduct extensive experiments, and the experimental results demonstrate the effectiveness