Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Online feature selection for rapid, low-overhead learning in networked systems
KTH Royal Institute of Technology, Sweden.
RISE Research Institutes of Sweden. KTH Royal Institute of Technology, Sweden.
RISE Research Institutes of Sweden, Digital Systems, Data Science. KTH Royal Institute of Technology, Sweden.ORCID iD: 0000-0001-6039-8493
2020 (English)In: 16th International Conference on Network and Service Management, CNSM 2020, 2nd International Workshop on Analytics for Service and Application Management, AnServApp 2020 and 1st International Workshop on the Future Evolution of Internet Protocols, IPFuture 2020, Institute of Electrical and Electronics Engineers Inc. , 2020Conference paper, Published paper (Refereed)
Abstract [en]

Data-driven functions for operation and management often require measurements collected through monitoring for model training and prediction. The number of data sources can be very large, which requires a significant communication and computing overhead to continuously extract and collect this data, as well as to train and update the machine-learning models. We present an online algorithm, called OSFS, that selects a small feature set from a large number of available data sources, which allows for rapid, low-overhead, and effective learning and prediction. OSFS is instantiated with a feature ranking algorithm and applies the concept of a stable feature set, which we introduce in the paper. We perform extensive, experimental evaluation of our method on data from an in-house testbed. We find that OSFS requires several hundreds measurements to reduce the number of data sources by two orders of magnitude, from which models are trained with acceptable prediction accuracy. While our method is heuristic and can be improved in many ways, the results clearly suggests that many learning tasks do not require a lengthy monitoring phase and expensive offline training.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2020.
Keywords [en]
Data-driven engineering, Dimensionality reduction, Machine learning (ML), E-learning, Forecasting, Heuristic methods, Internet protocols, Online systems, Effective learning, Experimental evaluation, Machine learning models, On-line algorithms, Online feature selection, Operation and management, Orders of magnitude, Prediction accuracy, Learning systems
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-51945DOI: 10.23919/CNSM50824.2020.9269066Scopus ID: 2-s2.0-85098668191ISBN: 9783903176317 (print)OAI: oai:DiVA.org:ri-51945DiVA, id: diva2:1521210
Conference
16th International Conference on Network and Service Management, CNSM 2020, 2nd International Workshop on Analytics for Service and Application Management, AnServApp 2020 and 1st International Workshop on the Future Evolution of Internet Protocols, IPFuture 2020, 2 November 2020 through 6 November 2020
Note

Funding details: VINNOVA; Funding text 1: VII. ACKNOWLEDGEMENTS The authors are grateful to Andreas Johnsson, Hannes Larsson, and Jalil Taghia with Ericsson Research for fruitful discussion around this work, as well as to Kim Hammar and Rodolfo Villac¸a for comments on an earlier version of this paper. This research has been partially supported by the Swedish Governmental Agency for Innovation Systems, VINNOVA, through project AutoDC.

Available from: 2021-01-22 Created: 2021-01-22 Last updated: 2021-11-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Stadler, Rolf

Search in DiVA

By author/editor
Stadler, Rolf
By organisation
RISE Research Institutes of SwedenData Science
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 31 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf