Scalable Distributed Stream Processing

By Mitch Cherniack, Hari Balakrishnan, M. Balazinska, Donald Carney, Ugur Çetintemel, Ying Xing, S. Zdonik. Conference on Innovative Data Systems Research, 2003

648 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/90a27218faad130adac4e195ebde63f46df4a2e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

High-performance complex event processing over streams (2006, methodology): “As aggregates over streams have been extensively studied in the field of stream processing [2][7] [9][13], we expect to adopt many stream processing techniques in our system.”
High-availability algorithms for distributed stream processing (2005, background): “We also analyze how the knowledge of query network properties can help decrease the cost of high availability.”
The Design of the Borealis Stream Processing Engine (2005, background): “If network bandwidth is a limited resource in the system, then “edge” boxes (which are easily slide-able [18]) are moved between upstream and downstream nodes.”
Operator Scheduling in a Data Stream Manager (2003, background): “We are also considering extending our scheduling techniques to distributed environments and other resources (such as bandwidth) in the context of Aurora* [10].”
Efficient pattern matching over event streams (2008, methodology): “In each stream, all events have the same type, stock, that contains three attributes, symbol, price, volume, with respective value ranges [1-2], [1-1000], [1-1000].”
Discretized streams: fault-tolerant streaming computation at scale (2013, methodology): “…D-Streams are primarily an execution strategy (describing how to break a computation into steps), they can be used to implement many of the standard operations in streaming systems, such as sliding windows and incremental processing [10, 4], by simply batching their execution into small timesteps.”
Live Video Analytics at Scale with Approximation and Delay-Tolerance (2017, methodology): “We considered streaming databases with approximation [19] [37] [68] as a starting point for our solution.”
Issues in data stream management (2003, background): “• Aurora [11, 19] is a workflow-oriented system that allows users to build query plans by arranging boxes (operators) and arrows (data flow among operators).”
Discretized Streams: An Efficient and Fault-Tolerant Model for Stream Processing on Large Clusters (2012, background): “Most current distributed stream processing systems, including Yahoo!’s S4 [19], Twitter’s Storm [21], and streaming databases [2, 3, 4], are based on a recordat-a-time processing model, where nodes receive each record, update internal state, and send out new records in response.”
A Framework for Partitioning and Execution of Data Stream Applications in Mobile Cloud Computing (2012, background): “By moving the computation to the cloud, many applications which could not be accommodated before due to the lack of signi.cant computation capability and energy power of mobile devices, will be made possible, while leveraging the stable and ample capacity of cloud.”
Network-Aware Operator Placement for Stream-Processing Systems (2006, background): “Distributed stream-processing systems (DSPSs), such as Borealis [7], Medusa [9], PIER [14], GATES [8], and Iris- Net [13], collect, process, and aggregate data across massive numbers of real-time streams.”
Infrastructure for Data Processing in Large-Scale Interconnected Sensor Networks (2007, background): “In the Aurora project [5] (http://www.”
Fault-tolerance in the Borealis distributed stream processing system (2005, background): “Stream processing applications are inherently distributed, both because input streams often arrive from geographically distributed data sources, and because running SPEs on multiple processing nodes enables better performance under high load [15, 35].”