Change search
ReferencesLink to record
Permanent link

Direct link
Predicting service metrics for cluster-based services using real-time analytics
KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre. KTH, School of Electrical Engineering (EES), Communication Networks. (Kommunikationsnät, Communication Networks)ORCID iD: 0000-0002-2680-9065
(Ericsson Research, Sweden)
(Swedish Institute of Computer Science (SICS), Sweden)
(Ericsson Research, Sweden)
Show others and affiliations
2015 (English)In: IFIP/IEEE 11th International Conference on Network and Service Management, CNSM 2015, Barcelona, Spain, November 9-13, 2015, IEEE conference proceedings, 2015Conference paper (Refereed)
Abstract [en]

Predicting the performance of cloud services is intrinsically hard. In this work, we pursue an approach based upon statistical learning, whereby the behaviour of a system is learned from observations. Specifically, our testbed implementation collects device statistics from a server cluster and uses a regression method that accurately predicts, in real-time, client-side service metrics for a video streaming service running on the cluster. The method is service-agnostic in the sense that it takes as input operating-systems statistics instead of service-level metrics. We show that feature set reduction significantly improves prediction accuracy in our case, while simultaneously reducing model computation time. We also discuss design and implementation of a real-time analytics engine, which processes streams of device statistics and service metrics from testbed sensors and produces model predictions through online learning.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015.
Keyword [en]
Quality of service, cloud computing, network analytics, statistical learning, machine learning
National Category
Communication Systems Computer Systems Telecommunications Computer Science
URN: urn:nbn:se:kth:diva-172795DOI: 10.1109/CNSM.2015.7367349ISI: 000379333700019ScopusID: 2-s2.0-84964055190OAI: diva2:849585
IFIP/IEEE 11th International Conference on Network and Service Management, CNSM 2015, Barcelona, Spain, November 9-13, 2015
VINNOVA, 2013-03895

QC 20151002

Available from: 2015-08-28 Created: 2015-08-28 Last updated: 2016-08-12Bibliographically approved

Open Access in DiVA

fulltext(595 kB)149 downloads
File information
File name FULLTEXT01.pdfFile size 595 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusConference website

Search in DiVA

By author/editor
Yanggratoke, RerngvitStadler, Rolf
By organisation
ACCESS Linnaeus CentreCommunication Networks
Communication SystemsComputer SystemsTelecommunicationsComputer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 149 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 1489 hits
ReferencesLink to record
Permanent link

Direct link