Modeling IP-to-IP communication using the weighted stochastic block model

Patrick Kalmbach; Lion Gleiter; Johannes Zerwas; Andreas Blenk; Wolfgang Kellerer; Stefan Schmid

doi:10.1145/3234200.3234245

Modeling IP-to-IP communication using the weighted stochastic block model

Patrick Kalmbach, Lion Gleiter, Johannes Zerwas, Andreas Blenk, Wolfgang Kellerer, Stefan Schmid

Chair of Communication Networks

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

3 Scopus citations

Abstract

The vision of self-driving networks integrates network measurements with network control. Processing data for each of the network control tasks separately might be prohibitive due to the large volume and waste of computational resources. In this work we make the case of using theWeighted Stochastic Block Model (WSBM), a probabilistic model, to learn a task independent representation. In particular, we consider a case study of real-world IP-to-IP communication. The learned representation provides higher level-features for traffic engineering, anomaly detection, or other tasks, and reduces their computational effort. We find that the WSBM is able to accurately model traffic and structure of communication in the considered trace.

Original language	English
Title of host publication	SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018
Publisher	Association for Computing Machinery, Inc
Pages	48-50
Number of pages	3
ISBN (Electronic)	9781450359153
DOIs	https://doi.org/10.1145/3234200.3234245
State	Published - 7 Aug 2018
Event	ACM SIGCOMM 2018 Conference - Budapest, Hungary Duration: 20 Aug 2018 → 25 Aug 2018

Publication series

Name	SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018

Conference

Conference	ACM SIGCOMM 2018 Conference
Country/Territory	Hungary
City	Budapest
Period	20/08/18 → 25/08/18

Keywords

Data analysis
Network monitoring
Stochastic block model

Access to Document

10.1145/3234200.3234245

Cite this

Kalmbach, P., Gleiter, L., Zerwas, J., Blenk, A., Kellerer, W., & Schmid, S. (2018). Modeling IP-to-IP communication using the weighted stochastic block model. In SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018 (pp. 48-50). (SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018). Association for Computing Machinery, Inc. https://doi.org/10.1145/3234200.3234245

@inproceedings{af7119cc96b04b688ce037d24b87ed0a,

title = "Modeling IP-to-IP communication using the weighted stochastic block model",

abstract = "The vision of self-driving networks integrates network measurements with network control. Processing data for each of the network control tasks separately might be prohibitive due to the large volume and waste of computational resources. In this work we make the case of using theWeighted Stochastic Block Model (WSBM), a probabilistic model, to learn a task independent representation. In particular, we consider a case study of real-world IP-to-IP communication. The learned representation provides higher level-features for traffic engineering, anomaly detection, or other tasks, and reduces their computational effort. We find that the WSBM is able to accurately model traffic and structure of communication in the considered trace.",

keywords = "Data analysis, Network monitoring, Stochastic block model",

author = "Patrick Kalmbach and Lion Gleiter and Johannes Zerwas and Andreas Blenk and Wolfgang Kellerer and Stefan Schmid",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; ACM SIGCOMM 2018 Conference ; Conference date: 20-08-2018 Through 25-08-2018",

year = "2018",

month = aug,

day = "7",

doi = "10.1145/3234200.3234245",

language = "English",

series = "SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018",

publisher = "Association for Computing Machinery, Inc",

pages = "48--50",

booktitle = "SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018",

}

Kalmbach, P, Gleiter, L, Zerwas, J, Blenk, A, Kellerer, W & Schmid, S 2018, Modeling IP-to-IP communication using the weighted stochastic block model. in SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018. SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018, Association for Computing Machinery, Inc, pp. 48-50, ACM SIGCOMM 2018 Conference, Budapest, Hungary, 20/08/18. https://doi.org/10.1145/3234200.3234245

Modeling IP-to-IP communication using the weighted stochastic block model. / Kalmbach, Patrick; Gleiter, Lion; Zerwas, Johannes et al.
SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, 2018. p. 48-50 (SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018).

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

TY - GEN

T1 - Modeling IP-to-IP communication using the weighted stochastic block model

AU - Kalmbach, Patrick

AU - Gleiter, Lion

AU - Zerwas, Johannes

AU - Blenk, Andreas

AU - Kellerer, Wolfgang

AU - Schmid, Stefan

PY - 2018/8/7

Y1 - 2018/8/7

N2 - The vision of self-driving networks integrates network measurements with network control. Processing data for each of the network control tasks separately might be prohibitive due to the large volume and waste of computational resources. In this work we make the case of using theWeighted Stochastic Block Model (WSBM), a probabilistic model, to learn a task independent representation. In particular, we consider a case study of real-world IP-to-IP communication. The learned representation provides higher level-features for traffic engineering, anomaly detection, or other tasks, and reduces their computational effort. We find that the WSBM is able to accurately model traffic and structure of communication in the considered trace.

AB - The vision of self-driving networks integrates network measurements with network control. Processing data for each of the network control tasks separately might be prohibitive due to the large volume and waste of computational resources. In this work we make the case of using theWeighted Stochastic Block Model (WSBM), a probabilistic model, to learn a task independent representation. In particular, we consider a case study of real-world IP-to-IP communication. The learned representation provides higher level-features for traffic engineering, anomaly detection, or other tasks, and reduces their computational effort. We find that the WSBM is able to accurately model traffic and structure of communication in the considered trace.

KW - Data analysis

KW - Network monitoring

KW - Stochastic block model

UR - http://www.scopus.com/inward/record.url?scp=85056485172&partnerID=8YFLogxK

U2 - 10.1145/3234200.3234245

DO - 10.1145/3234200.3234245

M3 - Conference contribution

AN - SCOPUS:85056485172

T3 - SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018

SP - 48

EP - 50

BT - SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018

PB - Association for Computing Machinery, Inc

T2 - ACM SIGCOMM 2018 Conference

Y2 - 20 August 2018 through 25 August 2018

ER -

Kalmbach P, Gleiter L, Zerwas J, Blenk A, Kellerer W, Schmid S. Modeling IP-to-IP communication using the weighted stochastic block model. In SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018. Association for Computing Machinery, Inc. 2018. p. 48-50. (SIGCOMM 2018 - Proceedings of the 2018 Posters and Demos, Part of SIGCOMM 2018). doi: 10.1145/3234200.3234245

Modeling IP-to-IP communication using the weighted stochastic block model

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this