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
Evaluation of Machine Learning Methods for Predicting Client Metrics for a Telecom Service
KTH, School of Engineering Sciences (SCI).
KTH, School of Engineering Sciences (SCI).
2017 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

A video streaming service faces several difficulties operating. Hardware is expensive and it is crucial to prioritize customers in a way that will make them content with the service provided. That is, deliver a sufficient frame rate and never allocate too much, essentially waste, resources on a client. This allocation has to be done several times per second so reading data from the client is out of the question, because the system would be adapting too slow. This raises the question whether it is possible to predict the frame rate of a client using only variables measured on the server and if it can be done efficiently. Which it can [1]. To further build on the work of Yanggratoke et al [1], we evaluated several different machine learning methods on a data set in terms of performance, training time and dependence on the size of the data set. Neural networks, having the best adapting capabilities, resulted in the best performance but training is more time consuming than for the linear model. Using neural networks is a good idea when the relationship between input and output is not linear.

Place, publisher, year, edition, pages
2017. , p. 13
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-219459OAI: oai:DiVA.org:kth-219459DiVA, id: diva2:1163215
Examiners
Available from: 2017-12-06 Created: 2017-12-06 Last updated: 2017-12-06Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Engineering Sciences (SCI)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 63 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