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
Spark-based Application for Abnormal Log Detection
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2014 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Ericsson is a world-leader in the rapidly-changing environment of communications technology and thus it is important to provide reliable and high quality networks. Automated test loops are executed frequently, trying to find problems  in Ericsson's products but, since test cases alone are not always adequate,  machine learning techniques  are sometimes  used to find abnormal system behaviour. The Awesome Automatic Log Analysis Application (AALAA) tries to find such behaviour by checking the log files produced during the testing, using machine learning techniques. Unfortunately,  its performance is not sufficient as it requires  a lot of time to process the logs and to train the model. This thesis manages to improve AALAAs performance by implementing a new version that uses Apache Spark, a general purpose  cluster  computing system, for both the processing of the data and for the training of the machine learning algorithm.

Place, publisher, year, edition, pages
2014.
Series
IT, 14 057
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-233335OAI: oai:DiVA.org:uu-233335DiVA: diva2:751988
Educational program
Master Programme in Energy Technology
Supervisors
Examiners
Available from: 2014-10-02 Created: 2014-10-02 Last updated: 2014-10-02Bibliographically approved

Open Access in DiVA

fulltext(659 kB)2225 downloads
File information
File name FULLTEXT01.pdfFile size 659 kBChecksum SHA-512
cb384f735b0b2cffc0f35934fdd2b33ec5b60b35f0c45153dd5bded64ea90a096a419b4c1868a66506356716f57e190cedabc7e7507f7384503db73374a95210
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 2225 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

urn-nbn

Altmetric score

urn-nbn
Total: 1958 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