DESTIN: Detecting State Transitions in Network elements

Parisa Foroughi; Wenqin Shao; Frank Brockners; Jean Louis Rougier

DESTIN: Detecting State Transitions in Network elements

Parisa Foroughi
, Wenqin Shao
, Frank Brockners
, Jean Louis Rougier

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes. Commonly, this assessment is achieved by performing regular checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. In this paper, a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)) is explored with an unsupervised approach. The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network device. The efficiency of the method is demonstrated on an experimental test-bed.

Original language	English
Title of host publication	Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management
Editors	Toufik Ahmed, Olivier Festor, Yacine Ghamri-Doudane, Joon-Myung Kang, Alberto E. Schaeffer-Filho, Abdelkader Lahmadi, Edmundo Madeira
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	161-169
Number of pages	9
ISBN (Electronic)	9783903176324
Publication status	Published - 17 May 2021
Event	17th IFIP/IEEE International Symposium on Integrated Network Management, IM 2021 - Virtual, Bordeaux, France Duration: 17 May 2021 → 21 May 2021

Publication series

Name	Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management

Conference

Conference	17th IFIP/IEEE International Symposium on Integrated Network Management, IM 2021
Country/Territory	France
City	Virtual, Bordeaux
Period	17/05/21 → 21/05/21

Keywords

Change detection
Machine learning
Network management
Principal angles

Cite this

Foroughi, P., Shao, W., Brockners, F., & Rougier, J. L. (2021). DESTIN: Detecting State Transitions in Network elements. In T. Ahmed, O. Festor, Y. Ghamri-Doudane, J.-M. Kang, A. E. Schaeffer-Filho, A. Lahmadi, & E. Madeira (Eds.), Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management (pp. 161-169). Article 9464016 (Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management). Institute of Electrical and Electronics Engineers Inc..

Foroughi, Parisa ; Shao, Wenqin ; Brockners, Frank et al. / DESTIN : Detecting State Transitions in Network elements. Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management. editor / Toufik Ahmed ; Olivier Festor ; Yacine Ghamri-Doudane ; Joon-Myung Kang ; Alberto E. Schaeffer-Filho ; Abdelkader Lahmadi ; Edmundo Madeira. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 161-169 (Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management).

@inproceedings{ad755554dd40460e92a0b54fb14b88ed,

title = "DESTIN: Detecting State Transitions in Network elements",

abstract = "Operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes. Commonly, this assessment is achieved by performing regular checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. In this paper, a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)) is explored with an unsupervised approach. The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network device. The efficiency of the method is demonstrated on an experimental test-bed.",

keywords = "Change detection, Machine learning, Network management, Principal angles",

author = "Parisa Foroughi and Wenqin Shao and Frank Brockners and Rougier, \{Jean Louis\}",

note = "Publisher Copyright: {\textcopyright} 2021 IFIP.; 17th IFIP/IEEE International Symposium on Integrated Network Management, IM 2021 ; Conference date: 17-05-2021 Through 21-05-2021",

year = "2021",

month = may,

day = "17",

language = "English",

series = "Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "161--169",

editor = "Toufik Ahmed and Olivier Festor and Yacine Ghamri-Doudane and Joon-Myung Kang and Schaeffer-Filho, \{Alberto E.\} and Abdelkader Lahmadi and Edmundo Madeira",

booktitle = "Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management",

}

Foroughi, P, Shao, W, Brockners, F & Rougier, JL 2021, DESTIN: Detecting State Transitions in Network elements. in T Ahmed, O Festor, Y Ghamri-Doudane, J-M Kang, AE Schaeffer-Filho, A Lahmadi & E Madeira (eds), Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management., 9464016, Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management, Institute of Electrical and Electronics Engineers Inc., pp. 161-169, 17th IFIP/IEEE International Symposium on Integrated Network Management, IM 2021, Virtual, Bordeaux, France, 17/05/21.

DESTIN: Detecting State Transitions in Network elements. / Foroughi, Parisa; Shao, Wenqin; Brockners, Frank et al.
Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management. ed. / Toufik Ahmed; Olivier Festor; Yacine Ghamri-Doudane; Joon-Myung Kang; Alberto E. Schaeffer-Filho; Abdelkader Lahmadi; Edmundo Madeira. Institute of Electrical and Electronics Engineers Inc., 2021. p. 161-169 9464016 (Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - DESTIN

T2 - 17th IFIP/IEEE International Symposium on Integrated Network Management, IM 2021

AU - Foroughi, Parisa

AU - Shao, Wenqin

AU - Brockners, Frank

AU - Rougier, Jean Louis

PY - 2021/5/17

Y1 - 2021/5/17

N2 - Operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes. Commonly, this assessment is achieved by performing regular checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. In this paper, a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)) is explored with an unsupervised approach. The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network device. The efficiency of the method is demonstrated on an experimental test-bed.

AB - Operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes. Commonly, this assessment is achieved by performing regular checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. In this paper, a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)) is explored with an unsupervised approach. The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network device. The efficiency of the method is demonstrated on an experimental test-bed.

KW - Change detection

KW - Machine learning

KW - Network management

KW - Principal angles

M3 - Conference contribution

AN - SCOPUS:85113702402

T3 - Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management

SP - 161

EP - 169

BT - Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management

A2 - Ahmed, Toufik

A2 - Festor, Olivier

A2 - Ghamri-Doudane, Yacine

A2 - Kang, Joon-Myung

A2 - Schaeffer-Filho, Alberto E.

A2 - Lahmadi, Abdelkader

A2 - Madeira, Edmundo

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 17 May 2021 through 21 May 2021

ER -

Foroughi P, Shao W, Brockners F, Rougier JL. DESTIN: Detecting State Transitions in Network elements. In Ahmed T, Festor O, Ghamri-Doudane Y, Kang JM, Schaeffer-Filho AE, Lahmadi A, Madeira E, editors, Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management. Institute of Electrical and Electronics Engineers Inc. 2021. p. 161-169. 9464016. (Proceedings of the IM 2021 - 2021 IFIP/IEEE International Symposium on Integrated Network Management).

DESTIN: Detecting State Transitions in Network elements

Abstract

Publication series

Conference

Keywords

Fingerprint

Cite this