SSC: cloud-based data stream management in distributed environments

Stream-oriented applications account for one of the major types of today's computing practices. They deal with high-speed data streams. When it comes to stream-oriented distributed systems, some challenges arise: for one thing, processing capability of a single compute node might become the bottleneck of the entire system. For another, transmitting streams among physically dispersed nodes could incur both communication overhead and instability of a distributed application. In this paper, we discuss the potential of using cloud technology to respond to various challenges faced by stream-oriented distributed systems. We introduce our idea of a special cloud, the scientific streaming cloud (SSC), which supports stream management in distributed environments. We also present our design of a language and an algorithm which are used on the SSC to describe and optimise stream-related tasks, respectively. Furthermore, we demonstrate our prototype implementation and a real-world application of the SSC.