Predicting service metrics for cluster-based services using real-time analytics

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...

Full description

Saved in:
Bibliographic Details
Published in:2015 11th International Conference on Network and Service Management (CNSM) pp. 135 - 143
Main Authors: Yanggratoke, Rerngvit, Ahmed, Jawwad, Ardelius, John, Flinta, Christofer, Johnsson, Andreas, Gillblad, Daniel, Stadler, Rolf
Format: Conference Proceeding
Language:English
Published: IFIP 01.11.2015
Subjects:
cloud computing
Computational modeling
machine learning
Measurement
network analytics
Predictive models
Quality of service
Real-time systems
Servers
Statistical learning
Yttrium
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract 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.
AbstractList 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.
Author Gillblad, Daniel
Ahmed, Jawwad
Flinta, Christofer
Yanggratoke, Rerngvit
Ardelius, John
Johnsson, Andreas
Stadler, Rolf
Author_xml – sequence: 1
  givenname: Rerngvit
  surname: Yanggratoke
  fullname: Yanggratoke, Rerngvit
  email: rerngvit@kth.se
  organization: ACCESS Linnaeus Center, KTH R. Inst. of Technol., Stockholm, Sweden
– sequence: 2
  givenname: Jawwad
  surname: Ahmed
  fullname: Ahmed, Jawwad
  email: jawwad.ahmed@ericsson.com
  organization: Ericsson Res., Stockholm, Sweden
– sequence: 3
  givenname: John
  surname: Ardelius
  fullname: Ardelius, John
  email: john@sics.se
  organization: Swedish Inst. of Comput. Sci. (SICS), Sweden
– sequence: 4
  givenname: Christofer
  surname: Flinta
  fullname: Flinta, Christofer
  email: christofer.flinta@ericsson.com
  organization: Ericsson Res., Stockholm, Sweden
– sequence: 5
  givenname: Andreas
  surname: Johnsson
  fullname: Johnsson, Andreas
  email: andreas.a.johnsson@ericsson.com
  organization: Ericsson Res., Stockholm, Sweden
– sequence: 6
  givenname: Daniel
  surname: Gillblad
  fullname: Gillblad, Daniel
  email: dgi@sics.se
  organization: Swedish Inst. of Comput. Sci. (SICS), Sweden
– sequence: 7
  givenname: Rolf
  surname: Stadler
  fullname: Stadler, Rolf
  email: stadler@kth.se
  organization: ACCESS Linnaeus Center, KTH R. Inst. of Technol., Stockholm, Sweden
BookMark eNo1j81KxDAUhSMoqGMfQNzkBVrz1yZZSlFHGB1BXQ83ya0E2o4kGWHe3hHHzfk25ztwLsnpvJ2RkGvOGs6Zve1f3p4bwXjbaNlpqewJqaw20jJujNBGnZMq5-iY6HSnNDMXZP2aMERf4vxJM6bv6JFOWFL0mQ7bRP24ywVT7SBj-G9kusu_QkIY6xInpDDDuC8H6YqcDTBmrI5ckI-H-_d-Wa_Wj0_93aqOQjFbW-2VYsxZE4TSrpVu6DQHE6TyCFy0Az9kMB5a5hw6JwBUaMELGayVUi7Izd9uRMTNV4oTpP3meFv-AFbsUMs
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CNSM.2015.7367349
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9783901882784
3901882782
9783901882777
3901882774
EndPage 143
ExternalDocumentID 7367349
Genre orig-research
GroupedDBID 6IE
6IL
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIB
RIC
RIE
RIL
ID FETCH-LOGICAL-i2409-97c4400b98d247b53bf671a8d34cea125f1a12d8ca50bbebb2aa4d5ac23d99333
IEDL.DBID RIE
IngestDate Wed Dec 20 05:19:19 EST 2023
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i2409-97c4400b98d247b53bf671a8d34cea125f1a12d8ca50bbebb2aa4d5ac23d99333
OpenAccessLink https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-172795
PageCount 9
ParticipantIDs ieee_primary_7367349
PublicationCentury 2000
PublicationDate 20151101
PublicationDateYYYYMMDD 2015-11-01
PublicationDate_xml – month: 11
  year: 2015
  text: 20151101
  day: 01
PublicationDecade 2010
PublicationTitle 2015 11th International Conference on Network and Service Management (CNSM)
PublicationTitleAbbrev CNSM
PublicationYear 2015
Publisher IFIP
Publisher_xml – name: IFIP
SSID ssib026764708
Score 1.7175845
Snippet Predicting the performance of cloud services is intrinsically hard. In this work, we pursue an approach based upon statistical learning, whereby the behaviour...
SourceID ieee
SourceType Publisher
StartPage 135
SubjectTerms cloud computing
Computational modeling
machine learning
Measurement
network analytics
Predictive models
Quality of service
Real-time systems
Servers
Statistical learning
Yttrium
Title Predicting service metrics for cluster-based services using real-time analytics
URI https://ieeexplore.ieee.org/document/7367349
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1t8eBJpRW_ycGjabNJmtmci-LFWlCht5KvlUJtpdv6-83sbiuCFy8hhITAJGEemTfzCLnlCsD6QjAjXGBKO86MdYaJIgI3wRSF8ZXYBIzH-XRqJi1yt8-FiTFW5LPYx24Vyw8rv8WvsgFIDVKZNmkD6DpXa3d3hAatgOdN4DLjZjAavzwhd2vYb9b9ElCp_MfD0f92Pia9n0Q8Otm7mBPSissueZ6sMbqCfGVa1k-dfqAwli9pgqDUL7ZY_YChgwq7GSVFhvs7TRhxwVBQnlosR4JFmnvk7eH-dfTIGl0ENk_-1zADXqWn50wehAI3lK7QkNk8SOWjTYilyFIbclQ7cC46J6xVYWi9kCHBESlPSWe5WsYzQrWDCgFmVoJyUpjMBJtbWwSuucvCOemiMWafdemLWWOHi7-HL8kh2rtO1bsinc16G6_Jgf_azMv1TXVe3xInmQk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA21CnpSacVvc_Bo2myS3WzOxVKxXQtW6K3ka6VQt9Jt_f3u7G4rghcvIYSEwCRhHpk38xC6p0JKbVNGFDOOiMhQorRRhKVeUuVUmipbik3IJImnUzVuoIddLoz3viSf-Q50y1i-W9oNfJV1JY8kF2oP7YdCMFpla21vD4tkJCSN69BlQFW3l7yOgL0VduqVvyRUSg_SP_7f3ieo_ZOKh8c7J3OKGj5roZfxCuIrwFjGefXY8QdIY9kcFyAU28UG6h8QcFFuOyPHwHF_xwVKXBCQlMcaCpJAmeY2eus_TnoDUisjkHnhgRVR0ori8RkVOyakCblJIxno2HFhvS4wSxoUrYtB78AYbwzTWrhQW8ZdAUg4P0PNbJn5c4QjI0sMGGguheFMBcrpWOvU0YiawF2gFhhj9lkVv5jVdrj8e_gOHQ4mo-Fs-JQ8X6EjsH2VuHeNmuvVxt-gA_u1nuer2_LsvgE3Q5xQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2015+11th+International+Conference+on+Network+and+Service+Management+%28CNSM%29&rft.atitle=Predicting+service+metrics+for+cluster-based+services+using+real-time+analytics&rft.au=Yanggratoke%2C+Rerngvit&rft.au=Ahmed%2C+Jawwad&rft.au=Ardelius%2C+John&rft.au=Flinta%2C+Christofer&rft.date=2015-11-01&rft.pub=IFIP&rft.spage=135&rft.epage=143&rft_id=info:doi/10.1109%2FCNSM.2015.7367349&rft.externalDocID=7367349