Temporal Restriction Query Optimization for Event Stream Processing

Abstract

The trend that organizations are linking Service Oriented Architecture (SOA) efforts closely to real-time processes makes research and industrial community increasingly focus on the SOA and Event Stream Processing (ESP) connection. ESP needs to correlate multiple continuous events involved in complex temporal relationship and attribute logic relationship to more abstract complex events in richer semantic. Due to high speed arrival rate of events and vast volume of registered complex event queries, memory consumption and incremental event query evaluation demand a comprehensive dedicate event stream processing framework with low-latency and high scalability. In this paper, we study problems of query optimization for ESP, especially topics on temporal restriction query. We first propose a framework to integrate ESP features with business process management and monitor. We then describe a query plan-based approach to efficiently execute ESP queries. Our approach uses algebraic conversion to efficiently handle temporal restriction queries, which are a key component of complex event processing, and computes temporal relevance condition at compile time to obtain event relevance time for a given expression. We demonstrate the effectiveness of our approach through a performance evaluation of our prototype implementation.