Back to Search

On spectral analysis of the Internet delay space and detecting anomalous routing paths

Title	On spectral analysis of the Internet delay space and detecting anomalous routing paths
Author	Gürsun, Gonca
Publication Date:	2019
Publication Place	- TÜBİTAK
Subject	Internet routing, Anomaly detection, Content delivery, Internet measurement
Type	Periodical
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	1303-6203
Record ID	56feed73-6927-44ca-b25a-823727eec42d
Library Location	Computer Science
Date	2019
Sample Text	Latency is one of the most critical performance metrics for a wide range of applications. Therefore, it is important to understand the underlying mechanisms that give rise to the observed latency values and diagnose the ones that are unexpectedly high. In this paper, we study the Internet delay space via robust principal component analysis (RPCA). Using RPCA, we show that the delay space, i.e. the matrix of measured round trip times between end hosts, can be decomposed into two components: the estimated latency between end hosts with respect to the current state of the Internet and the inflation on the paths between the end hosts. Using this decomposition, first we study the wellknown low-dimensionality phenomena of the delay space and ask what properties of the end hosts define the dimensions. Second, using the decomposition, we develop a filtering method to detect the paths that experience unexpected latencies and identify routing anomalies. We show that our filter successfully identifies an anomalous route even when its observed latency is not obviously high in magnitude.
Cilt	27

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

On spectral analysis of the Internet delay space and detecting anomalous routing paths

Author Gürsun, Gonca

Publication Date 2019

Publication Place - TÜBİTAK

Subject Internet routing, Anomaly detection, Content delivery, Internet measurement

Type Periodical

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 1303-6203

Record ID 56feed73-6927-44ca-b25a-823727eec42d

Library Location Computer Science

Date 2019

Sample Text Latency is one of the most critical performance metrics for a wide range of applications. Therefore, it is important to understand the underlying mechanisms that give rise to the observed latency values and diagnose the ones that are unexpectedly high. In this paper, we study the Internet delay space via robust principal component analysis (RPCA). Using RPCA, we show that the delay space, i.e. the matrix of measured round trip times between end hosts, can be decomposed into two components: the estimated latency between end hosts with respect to the current state of the Internet and the inflation on the paths between the end hosts. Using this decomposition, first we study the wellknown low-dimensionality phenomena of the delay space and ask what properties of the end hosts define the dimensions. Second, using the decomposition, we develop a filtering method to detect the paths that experience unexpected latencies and identify routing anomalies. We show that our filter successfully identifies an anomalous route even when its observed latency is not obviously high in magnitude.

Cilt 27