BridgeNet: An Adaptive Multi-Source Stream Dissemination Overlay Network
IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications
Emerging stream processing applications such as on-line data analysis often need to acquire streaming information from geographically dispersed locations (e.g., different sensor networks). Different from conventional discrete data (e.g., messages), streaming data are often time-varying and long-lived, which provides both new challenges and opportunities for optimizing wide-area continuous information dissemination. In this paper, we present BridgeNet, a novel adaptive multi-source stream
... nation overlay network, which can efficiently collect streaming information from distributed locations and disseminate aggregated information to different stream consumers. BridgeNet provides a new distributed cell tree structure for multi-source stream aggregations, which can adaptively expand or contract itself in response to workload changes. In particular, Brid-geNet performs stream-pattern-based cell tree adaptations, stream clustering, and overlay topology adaptations to deliver efficient stream dissemination without losing system stability. For failure resilience, BridgeNet provides light-weight backup schemes to achieve fast failure recovery. We have implemented a prototype of BridgeNet and conducted extensive experiments using both simulations and Planetlab deployment. The experimental results based on both synthetic workload and real data streams show that BridgeNet outperforms existing schemes for efficient multisource stream dissemination.