Reference : NETPerfTrace – Predicting Internet Path Dynamics and Performance with Machine Learning
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/211667
NETPerfTrace – Predicting Internet Path Dynamics and Performance with Machine Learning
English
Wassermann, Sarah mailto [Université de Liège - ULiège > > > Master sc. informatiques, à fin.]
Casas, Pedro [> >]
Cuvelier, Thibaut mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation : Optimisation discrète >]
Donnet, Benoît mailto [Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorithmique des grands systèmes >]
Aug-2017
Proceedings of Big-DAMA ’17
Yes
International
Big-DAMA '17: Workshop on Big Data Analytics and Machine Learning for Data Communication Networks
21-08-2017
Los Angeles
CA
[en] network performance modeling ; supervised learning ; feature selection ; distributed measurements ; machine learning ; traceroute ; M-Lab ; DTRACK
[en] We study the problem of predicting Internet path changes and path performance using traceroute measurements and machine learning models. Path changes are frequently linked to path inflation and performance degradation, therefore the relevance of the problem. We introduce NETPerfTrace, an Internet Path Tracking system to forecast path changes and path latency variations. By relying on decision trees and using empirical distribution-based input features, we show that NETPerfTrace can predict (i) the remaining life time of a path before it actually changes and (ii) the number of path changes in a certain time period with relatively high accuracy. Through extensive evaluation, we demonstrate that NETPerfTrace highly outperforms DTRACK, a previous system with the same prediction targets. NETPerfTrace also offers path performance forecasting capabilities. In particular, our tool can predict path latency metrics, providing a system which can not only predict path changes, but also forecast their impact in terms of performance variations. We release NETPerfTrace as open software to the networking community, as well as all evaluation datasets.
WWFT
BigDAMA
Researchers
http://hdl.handle.net/2268/211667
10.1145/3098593.3098599

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
full_paper_embedded.pdfAuthor preprint394.01 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.