Computing (2018) 100:1–2 https://doi.org/10.1007/s00607-018-0586-9 EDITORIAL A note on resource management techniques and systems for big data workﬂow processing 1 2 Rajiv Ranjan · Prem Prakash Jayaraman · 3 2 Massimo Villari · Dimitrios Georgakopoulos Published online: 13 February 2018 © Springer-Verlag GmbH Austria, part of Springer Nature 2018 The continuous shift towards data-driven enterprises and the necessity of getting real-time insights from streaming data (e.g. tweets, web clicks) has expedited the development of dozens of big data analytics workﬂows (e.g. click-stream analyt- ics). Resource management of such analytics workﬂows is vital, since it enables cost-effective usage of cloud services against unpredictable time-varying workloads (characterised by 3Vs—volume, velocity and veracity). A typical streaming data ana- lytics workﬂow consists of three layers: data ingestion, analytics, and storage, each of which is backed by different data processing platforms (e.g. Amazon Kinesis, Apache Storm, DynamoDB, respectively) and is served by different cloud services (e.g. VM, Queues). Moreover, the application workloads processed by the data analytics work- ﬂows are heterogeneous and demand different performance and quality of service measures. Hence, elasticity management of various resources for such big data ana- lytics workﬂow is both difﬁcult and challenging. B Rajiv Ranjan email@example.com Prem Prakash Jayaraman
Computing – Springer Journals
Published: Feb 13, 2018
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 12 million articles from more than
10,000 peer-reviewed journals.
All for just $49/month
It’s easy to organize your research with our built-in tools.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud