Paper published in a book (Scientific congresses and symposiums)
Machine Learning based Prediction of Internet Path Dynamics
Wassermann, Sarah; Casas, Pedro; Donnet, Benoît
2016In ACM CoNEXT Student Workshop: Irvine 12 décembre 2016
Peer reviewed


Full Text
Author preprint (8.33 MB)

All documents in ORBi are protected by a user license.

Send to


Keywords :
Traceroute; Change Prediction; Machine Learning
Abstract :
[en] We study the problem of predicting Internet path changes and path performance using traceroute and machine-learning techniques. Path changes are frequently linked to path inflation and performance degradation. Therefore, predicting their occurrence could improve the analysis of path dynamics using traceroute. By relying on neural networks and using empirical distribution based input features, we show that we are able to predict (i) the remaining life time of a path before it actually changes, and (ii) the number of path changes in a certain time slot with relatively high accuracy. We also show that it is possible to predict path performance in terms of latency, opening the door to novel, machine-learning-based approaches for RTT prediction.
Disciplines :
Computer science
Author, co-author :
Wassermann, Sarah ;  Université de Liège - ULiège > Master sc. informatiques, à fin.
Casas, Pedro
Donnet, Benoît  ;  Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorithmique des grands systèmes
Language :
Title :
Machine Learning based Prediction of Internet Path Dynamics
Publication date :
December 2016
Event name :
ACM CoNEXT Student Workshop
Event place :
Irvine, United States - California
Event date :
12 décembre 2016
Audience :
Main work title :
ACM CoNEXT Student Workshop: Irvine 12 décembre 2016
Peer reviewed :
Peer reviewed
Available on ORBi :
since 03 November 2016


Number of views
217 (15 by ULiège)
Number of downloads
222 (7 by ULiège)


Similar publications

Contact ORBi