2019
DOI: 10.1145/3303849
|View full text |Cite
|
Sign up to set email alerts
|

A Comprehensive Survey on Parallelization and Elasticity in Stream Processing

Abstract: Stream Processing (SP) has evolved as the leading paradigm to process and gain value from the high volume of streaming data produced e.g. in the domain of the Internet of ings. An SP system is a middleware that deploys a network of operators between data sources, such as sensors, and the consuming applications. SP systems typically face intense and highly dynamic data streams. Parallelization and elasticity enables SP systems to process these streams with continuously high quality of service. e current researc… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
62
2

Year Published

2019
2019
2022
2022

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 85 publications
(64 citation statements)
references
References 145 publications
(244 reference statements)
0
62
2
Order By: Relevance
“…Dayarathna et al [34] focus on the system architecture and use cases of stream processing platforms and only briefly discuss performance scalability. A more recent survey [99] proposes a classification for parallelization and elasticity methods in stream processing systems but lacks any discussion on automatic parameter tuning. Autonomic computing brings together the work of computer science and control communities with the purpose of developing autonomic systems, i.e., systems that can manage themselves automatically.…”
Section: Classification Of Approachesmentioning
confidence: 99%
“…Dayarathna et al [34] focus on the system architecture and use cases of stream processing platforms and only briefly discuss performance scalability. A more recent survey [99] proposes a classification for parallelization and elasticity methods in stream processing systems but lacks any discussion on automatic parameter tuning. Autonomic computing brings together the work of computer science and control communities with the purpose of developing autonomic systems, i.e., systems that can manage themselves automatically.…”
Section: Classification Of Approachesmentioning
confidence: 99%
“…This aggregation requires application of various data summarization techniques [71] including sampling, sketching, histograms, wavelets and adaptation of these techniques to meet the constraints of the hardware and the time-varying channel conditions. Henriette et al [280] investigated the state-of-theart stream processing systems that can be used to implement these data summarization techniques and execute them in a parallel and elastic manner. However, it still requires a lot of effort to develop new data summarization techniques and stream processing systems to handle the difficulty of processing high volumes data from various sources with multi-modality.…”
Section: Data Collectionmentioning
confidence: 99%
“…As most approaches applying stream processing, our presented approach is primarily based on data parallelism [2], meaning that (sub)topologies exist in multiple instances, each processing a portion of the data. Pipe-and-Filter frameworks such as TeeTime [25] employ task parallelism, where the individual filters (operators) are executed in parallel.…”
Section: Related Workmentioning
confidence: 99%
“…Stream processing [1,2] has evolved as a paradigm to process and analyze continuous streams of data, for example, coming from IoT sensors. The rapid development of stream processing engines [3] over the last years has paved the way for applications that process data exclusively online, i.e., as soon as it is recorded.…”
Section: Introductionmentioning
confidence: 99%