liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Finding Correlation and Predicting System Behavior in Large IT Infrastructure
Linköping University, Department of Computer and Information Science, Software and Systems. Linköping University, The Institute of Technology.
2014 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Modern IT development infrastructure has a large number of components that must be monitored, for instance servers and network components. Various system-metrics (build time, CPU utilization, queries time etc.) are gathered to monitor system performance. In practice, it is extremely difficult for a system administrator to observe a correlation between several systemmetrics and predict a target system-metric based on highly correlated system-metrics without machine learning support.

The experiments were performed on development logs at Ericsson. There were many system-metrics available in the system. Our goal is use machine learning techniques to find correlation between buildtime and other system-metrics and predict its trends in the future.

Place, publisher, year, edition, pages
2014. , 48 p.
Keyword [en]
Correlation, Prediction, Time series, PCA, Automation
National Category
Computer Systems
URN: urn:nbn:se:liu:diva-112850ISRN: LIU-IDA/ LITH-EX-A--13/024--SE, SaSOAI: diva2:772760
External cooperation
Ericsson AB
Subject / course
Master's programme in Computer Science
Available from: 2014-12-17 Created: 2014-12-17 Last updated: 2014-12-17Bibliographically approved

Open Access in DiVA

fulltext(727 kB)70 downloads
File information
File name FULLTEXT01.pdfFile size 727 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Hussain, Shahbaz
By organisation
Software and SystemsThe Institute of Technology
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 70 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

Total: 157 hits
ReferencesLink to record
Permanent link

Direct link