Flexible time management in data stream systems
By Utkarsh Srivastava, Jennifer Widom. ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, 2004
299 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing
View Paper: https://www.semanticscholar.org/paper/a7dced894b4d45488bf7f61942c1fd8dce7304ba
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ion Stoica
- Haoyuan Li
- Johannes Gehrke
- Kristin Tufte
- Matei A. Zaharia
- Scott Shenker
- Samuel Madden
- Hari Balakrishnan
In Computer Networks and Communications
- Ion Stoica
- Scott Shenker
- Samuel Madden
- Matei A. Zaharia
- Hari Balakrishnan
- M. Stonebraker
- Daniel J. Abadi
- Johannes Gehrke
In Signal Processing
- Samuel Madden
- Johannes Gehrke
- Mirek Riedewald
- Ion Stoica
- S. Zdonik
- Scott Shenker
- Ugur Çetintemel
- Kristin Tufte
Citations in the corpus
- MillWheel: Fault-Tolerant Stream Processing at Internet Scale (2013, background): “This inefficiency is high-lighted by Srivastava, et al, in [29], which discusses the maintenance of per-stream heartbeat arrays at every operator.”
- Cayuga: A General Purpose Event Monitoring System (2007, background): “A more sophisticated (but less efficient) approach is described in [15].”
- Semantics and evaluation techniques for window aggregates in data streams (2005, background): “To evaluate sliding-window aggregate queries where consecutive window extents overlap (i.e., each tuple belongs to multiple window extents), most current proposals keep all active input tuples in an in-memory buffer.”
- Fault-tolerance in the Borealis distributed stream processing system (2005, methodology): “SUnion is similar to the Input Manager in STREAM [36], which sorts tuples by increasing timestamp order and deduces heartbeats if applications do not provide them.”
- The Design of the Borealis Stream Processing Engine (2005, methodology): “Some techniques use punctuations [45], heartbeats [42], or statically defined slack [2] to tolerate bounded disorder and delays on input streams.”
- Discretized streams: fault-tolerant streaming computation at scale (2013, background): “They have been studied in detail in databases [23, 36].”
- The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing (2015, background): “CEDR [8] and Trill [13] are noteworthy in that they not only provide useful triggering semantics via punctuations [30, 28], but also provide an overall incremental model that is quite similar to the one we propose here; however, their windowing semantics are insufficient to express sessions, and the”