NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters

Liron Schiff, Ofri Ziv, Manfred Jaeger, Stefan Schmid

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Companies often have very limited information about the applications running in their datacenter or public/private cloud environments. As this can harm efficiency, performance, and security, many
network administrators work hard to manually assign actionable
description to (virtual) machines.
This paper presents and evaluates NetSlicer , a machine-learning
approach that enables an automated grouping of nodes into applications and their tiers. Our solution is based solely on the available
network layer data which is used as part of a novel graph clustering
algorithm, tailored toward the datacenter use case and accounting
also for observed port numbers. For the sake of this paper, we also
performed an extensive empirical measurement study, collecting
actual workloads from different production datacenters (data to
be released together with this paper). We find that our approach
features a high accuracy.
Original languageEnglish
Title of host publicationBig-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018
Number of pages6
PublisherAssociation for Computing Machinery
Publication date7 Aug 2018
Pages21-26
ISBN (Electronic)978-1-4503-5904-7
DOIs
Publication statusPublished - 7 Aug 2018
Event2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks: Big-DAMA - Budapest, Hungary
Duration: 20 Aug 201820 Aug 2018

Conference

Conference2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks
CountryHungary
CityBudapest
Period20/08/201820/08/2018

Fingerprint

Industry
Virtual machine

Keywords

  • Big data
  • Computer networks
  • Machine learning

Cite this

Schiff, L., Ziv, O., Jaeger, M., & Schmid, S. (2018). NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters. In Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018 (pp. 21-26). Association for Computing Machinery. https://doi.org/10.1145/3229607.3229614
Schiff, Liron ; Ziv, Ofri ; Jaeger, Manfred ; Schmid, Stefan. / NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters. Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018. Association for Computing Machinery, 2018. pp. 21-26
@inproceedings{1084506ad75b4e9e9214421380ee7e5c,
title = "NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters",
abstract = "Companies often have very limited information about the applications running in their datacenter or public/private cloud environments. As this can harm efficiency, performance, and security, manynetwork administrators work hard to manually assign actionabledescription to (virtual) machines.This paper presents and evaluates NetSlicer , a machine-learningapproach that enables an automated grouping of nodes into applications and their tiers. Our solution is based solely on the availablenetwork layer data which is used as part of a novel graph clusteringalgorithm, tailored toward the datacenter use case and accountingalso for observed port numbers. For the sake of this paper, we alsoperformed an extensive empirical measurement study, collectingactual workloads from different production datacenters (data tobe released together with this paper). We find that our approachfeatures a high accuracy.",
keywords = "Big data, Computer networks, Machine learning",
author = "Liron Schiff and Ofri Ziv and Manfred Jaeger and Stefan Schmid",
year = "2018",
month = "8",
day = "7",
doi = "10.1145/3229607.3229614",
language = "English",
pages = "21--26",
booktitle = "Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018",
publisher = "Association for Computing Machinery",
address = "United States",

}

Schiff, L, Ziv, O, Jaeger, M & Schmid, S 2018, NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters. in Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018. Association for Computing Machinery, pp. 21-26, 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Budapest, Hungary, 20/08/2018. https://doi.org/10.1145/3229607.3229614

NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters. / Schiff, Liron; Ziv, Ofri; Jaeger, Manfred; Schmid, Stefan.

Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018. Association for Computing Machinery, 2018. p. 21-26.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters

AU - Schiff, Liron

AU - Ziv, Ofri

AU - Jaeger, Manfred

AU - Schmid, Stefan

PY - 2018/8/7

Y1 - 2018/8/7

N2 - Companies often have very limited information about the applications running in their datacenter or public/private cloud environments. As this can harm efficiency, performance, and security, manynetwork administrators work hard to manually assign actionabledescription to (virtual) machines.This paper presents and evaluates NetSlicer , a machine-learningapproach that enables an automated grouping of nodes into applications and their tiers. Our solution is based solely on the availablenetwork layer data which is used as part of a novel graph clusteringalgorithm, tailored toward the datacenter use case and accountingalso for observed port numbers. For the sake of this paper, we alsoperformed an extensive empirical measurement study, collectingactual workloads from different production datacenters (data tobe released together with this paper). We find that our approachfeatures a high accuracy.

AB - Companies often have very limited information about the applications running in their datacenter or public/private cloud environments. As this can harm efficiency, performance, and security, manynetwork administrators work hard to manually assign actionabledescription to (virtual) machines.This paper presents and evaluates NetSlicer , a machine-learningapproach that enables an automated grouping of nodes into applications and their tiers. Our solution is based solely on the availablenetwork layer data which is used as part of a novel graph clusteringalgorithm, tailored toward the datacenter use case and accountingalso for observed port numbers. For the sake of this paper, we alsoperformed an extensive empirical measurement study, collectingactual workloads from different production datacenters (data tobe released together with this paper). We find that our approachfeatures a high accuracy.

KW - Big data

KW - Computer networks

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85056412507&partnerID=8YFLogxK

U2 - 10.1145/3229607.3229614

DO - 10.1145/3229607.3229614

M3 - Article in proceeding

SP - 21

EP - 26

BT - Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018

PB - Association for Computing Machinery

ER -

Schiff L, Ziv O, Jaeger M, Schmid S. NetSlicer: Automated and Traffic-Pattern Based Application Clustering in Datacenters. In Big-DAMA 2018 - Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, Part of SIGCOMM 2018. Association for Computing Machinery. 2018. p. 21-26 https://doi.org/10.1145/3229607.3229614