CEPaaS: Complex Event Processing as a Service
Proc. of the IEEE BigData Congress 2017
Complex Event Processing (CEP) is a technology for performing continuous operations on fast and distributed streams of data. By using CEP, companies can obtain real-time insights, create competitive advantage, and, ultimately unlock the potential of Big Data. Nevertheless, despite this recent surge of interest, the CEP market is still dominated by solutions that are costly and inflexible or too low-level and hard to operate. To overcome these adoption barriers, this research proposes the creation of a CEP as a Service (CEPaaS) system to provide CEP functionalities to users together with the advantages of the Software as a Service (SaaS) model, such as no up-front investment and low maintenance cost. To ensure the success of such a system, however, many complex requirements must be satisfied, such as low latency processing, fault tolerance, and query execution isolation. To satisfy these requirements, this paper also presents an architecture and implementation for this CEPaaS system based on three main pillars: multi-cloud architecture, container management systems, and extensible multi-tenant design. Experimental results demonstrate that the proposed system achieves the goal of offering CEP functionalities as a scalable and fault-tolerant service.