多源复杂事件检测中查询计划生成与优化技术的研究

Research on Query Plan Generation and Optimization in Multi-Source Complex Event Detection

摘要: 复杂事件处理技术是流数据查询的常见手段，随着数据多元化的发展，查询的复杂度急剧提升，其处理性能面临极大地挑战。为了提高多源复杂事件查询的处理效率，本文提出一种新的查询分解方案，提高集群资源利用率；针对事件源匹配，将查询中的筛选与事件源匹配中的筛选相结合设计了专用优化方案。实验证明以上方法能够有效地提高复杂事件查询效率。

Abstract: Complex event processing technology is a common method of streaming data query. With the development of data diversification, the complexity of query increases dramatically, and its processing performance is greatly challenged. In order to improve the processing efficiency of multi-source complex event query, this paper proposes a new query decomposition scheme to improve the utilization rate of cluster resources. For the matching of event sources, we combine the filtering in query with the filtering in event source matching to design a special optimization program. Experimental results show that the above method can effectively improve the efficiency of complex event query.