Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Performance prediction in dynamic clouds using transfer learning
Ericsson Research, Sweden.
RISE - Research Institutes of Sweden, ICT, SICS.ORCID iD: 0000-0001-6039-8493
Ericsson Research, Sweden.
2019 (English)In: 2019 IFIP/IEEE Symposium on Integrated Network and Service Management, IM 2019, Institute of Electrical and Electronics Engineers Inc. , 2019, p. 242-250Conference paper, Published paper (Refereed)
Abstract [en]

Learning a performance model for a cloud service is challenging since its operational environment changes during execution, which requires re-training of the model in order to maintain prediction accuracy. Training a new model from scratch generally involves extensive new measurements and often generates a data-collection overhead that negatively affects the service performance.In this paper, we investigate an approach for re-training neural-network models, which is based on transfer learning. Under this approach, a limited number of neural-network layers are re-trained while others remain unchanged. We study the accuracy of the re-trained model and the efficiency of the method with respect to the number of re-trained layers and the number of new measurements. The evaluation is performed using traces collected from a testbed that runs a Video-on-Demand service and a Key-Value Store under various load conditions. We study model re-training after changes in load pattern, infrastructure configuration, service configuration, and target metric. We find that our method significantly reduces the number of new measurements required to compute a new model after a change. The reduction exceeds an order of magnitude in most cases.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2019. p. 242-250
Keywords [en]
Machine Learning, Neural Networks, Performance Prediction, Service Management, Transfer Learning, Forecasting, Learning systems, Video on demand, Neural network model, Operational environments, Prediction accuracy, Service configuration, Video on demand services, Network layers
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-39272Scopus ID: 2-s2.0-85067071723ISBN: 9783903176157 (print)OAI: oai:DiVA.org:ri-39272DiVA, id: diva2:1334735
Conference
2019 IFIP/IEEE Symposium on Integrated Network and Service Management, IM 2019, 8 April 2019 through 12 April 2019
Note

Funding details: VINNOVA; Funding text 1: ACKNOWLEDGMENT The authors are grateful to Jawwad Ahmed and Christofer Flinta, both at Ericsson Research, and Forough Shahab Samani at KTH for fruitful discussions around this work. This research has been partially supported by the Swedish Governmental Agency for Innovation Systems, VINNOVA, through projects Celtic SENDATE EXTEND and ITEA3 AutoDC.

Available from: 2019-07-03 Created: 2019-07-03 Last updated: 2019-07-03Bibliographically approved

Open Access in DiVA

No full text in DiVA

Scopus

Authority records BETA

Stadler, Rolf

Search in DiVA

By author/editor
Stadler, Rolf
By organisation
SICS
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 3 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
v. 2.35.7