Machine Learning in Software Defined Networks: Data collection and traffic classification

Pedro Miguel Figueiredo Amaral; João  Dinis; Paulo da Costa Luís da Fonseca Pinto; L. Bernardo; João  Tavares; Henrique Mamede

doi:10.1109/ICNP.2016.7785327

Machine Learning in Software Defined Networks: Data collection and traffic classification

Pedro Miguel Figueiredo Amaral, João Dinis, Paulo da Costa Luís da Fonseca Pinto, L. Bernardo, João Tavares, Henrique Mamede

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

92 Citations (Scopus)

Abstract

Software Defined Networks (SDNs) provides a separation between the control plane and the forwarding plane of networks. The software implementation of the control plane and the built in data collection mechanisms of the OpenFlow protocol promise to be excellent tools to implement Machine Learning (ML) network control applications. A first step in that direction is to understand the type of data that can be collected in SDNs and how information can be learned from that data. In this work we describe a simple architecture deployed in an enterprise network that gathers traffic data using the OpenFlow protocol. We present the data-sets that can be obtained and show how several ML techniques can be applied to it for traffic classification. The results indicate that high accuracy classification can be obtained with the data-sets using supervised learning.

Original language	English
Title of host publication	2016 IEEE 24th International Conference on Network Protocols (ICNP)
Place of Publication	New York
Publisher	IEEE
ISBN (Electronic)	978-1-5090-3281-5
ISBN (Print)	978-1-5090-3282-2
DOIs	https://doi.org/10.1109/ICNP.2016.7785327
Publication status	Published - 14 Dec 2016
Event	24th IEEE International Conference on Network Protocols (ICNP) - Singapore, Singapore Duration: 8 Nov 2016 → 11 Nov 2016 Conference number: 24th

Publication series

Name	IEEE International Conference on Network Protocols Proceedings
Publisher	IEEE
Volume	2016-December
ISSN (Print)	1092-1648

Conference

Conference	24th IEEE International Conference on Network Protocols (ICNP)
Abbreviated title	ICNP
Country/Territory	Singapore
City	Singapore
Period	8/11/16 → 11/11/16

Keywords

Data Analysis
Machine Learning
Software defined Networks
Traffic Classification

Access to Document

10.1109/ICNP.2016.7785327Licence: Unspecified

Cite this

Amaral, P. M. F., Dinis, J., Pinto, P. D. C. L. D. F., Bernardo, L., Tavares, J., & Mamede, H. (2016). Machine Learning in Software Defined Networks: Data collection and traffic classification. In 2016 IEEE 24th International Conference on Network Protocols (ICNP) [7785327] (IEEE International Conference on Network Protocols Proceedings; Vol. 2016-December). IEEE. https://doi.org/10.1109/ICNP.2016.7785327

Amaral, Pedro Miguel Figueiredo ; Dinis, João ; Pinto, Paulo da Costa Luís da Fonseca ; Bernardo, L. ; Tavares, João ; Mamede, Henrique. / Machine Learning in Software Defined Networks : Data collection and traffic classification. 2016 IEEE 24th International Conference on Network Protocols (ICNP). New York : IEEE, 2016. (IEEE International Conference on Network Protocols Proceedings).

@inproceedings{20a6abc085dd41c4af29ffdde821dcbd,

title = "Machine Learning in Software Defined Networks: Data collection and traffic classification",

abstract = "Software Defined Networks (SDNs) provides a separation between the control plane and the forwarding plane of networks. The software implementation of the control plane and the built in data collection mechanisms of the OpenFlow protocol promise to be excellent tools to implement Machine Learning (ML) network control applications. A first step in that direction is to understand the type of data that can be collected in SDNs and how information can be learned from that data. In this work we describe a simple architecture deployed in an enterprise network that gathers traffic data using the OpenFlow protocol. We present the data-sets that can be obtained and show how several ML techniques can be applied to it for traffic classification. The results indicate that high accuracy classification can be obtained with the data-sets using supervised learning.",

keywords = "Data Analysis, Machine Learning, Software defined Networks, Traffic Classification",

author = "Amaral, {Pedro Miguel Figueiredo} and Jo{\~a}o Dinis and Pinto, {Paulo da Costa Lu{\'i}s da Fonseca} and L. Bernardo and Jo{\~a}o Tavares and Henrique Mamede",

note = "Sem PDF conforme despacho. This work was supported by the LoCoSDN project financed by FCT/MEC Project IT PEst-UID/EEA/50008/2013; 24th IEEE International Conference on Network Protocols (ICNP), ICNP ; Conference date: 08-11-2016 Through 11-11-2016",

year = "2016",

month = dec,

day = "14",

doi = "10.1109/ICNP.2016.7785327",

language = "English",

isbn = "978-1-5090-3282-2",

series = "IEEE International Conference on Network Protocols Proceedings",

publisher = "IEEE",

booktitle = "2016 IEEE 24th International Conference on Network Protocols (ICNP)",

}

Amaral, PMF, Dinis, J, Pinto, PDCLDF , Bernardo, L, Tavares, J & Mamede, H 2016, Machine Learning in Software Defined Networks: Data collection and traffic classification. in 2016 IEEE 24th International Conference on Network Protocols (ICNP)., 7785327, IEEE International Conference on Network Protocols Proceedings, vol. 2016-December, IEEE, New York, 24th IEEE International Conference on Network Protocols (ICNP), Singapore, Singapore, 8/11/16. https://doi.org/10.1109/ICNP.2016.7785327

Machine Learning in Software Defined Networks : Data collection and traffic classification. / Amaral, Pedro Miguel Figueiredo; Dinis, João ; Pinto, Paulo da Costa Luís da Fonseca ; Bernardo, L.; Tavares, João ; Mamede, Henrique.

2016 IEEE 24th International Conference on Network Protocols (ICNP). New York : IEEE, 2016. 7785327 (IEEE International Conference on Network Protocols Proceedings; Vol. 2016-December).

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

TY - GEN

T1 - Machine Learning in Software Defined Networks

T2 - 24th IEEE International Conference on Network Protocols (ICNP)

AU - Amaral, Pedro Miguel Figueiredo

AU - Dinis, João

AU - Pinto, Paulo da Costa Luís da Fonseca

AU - Bernardo, L.

AU - Tavares, João

AU - Mamede, Henrique

N1 - Conference code: 24th

PY - 2016/12/14

Y1 - 2016/12/14

N2 - Software Defined Networks (SDNs) provides a separation between the control plane and the forwarding plane of networks. The software implementation of the control plane and the built in data collection mechanisms of the OpenFlow protocol promise to be excellent tools to implement Machine Learning (ML) network control applications. A first step in that direction is to understand the type of data that can be collected in SDNs and how information can be learned from that data. In this work we describe a simple architecture deployed in an enterprise network that gathers traffic data using the OpenFlow protocol. We present the data-sets that can be obtained and show how several ML techniques can be applied to it for traffic classification. The results indicate that high accuracy classification can be obtained with the data-sets using supervised learning.

AB - Software Defined Networks (SDNs) provides a separation between the control plane and the forwarding plane of networks. The software implementation of the control plane and the built in data collection mechanisms of the OpenFlow protocol promise to be excellent tools to implement Machine Learning (ML) network control applications. A first step in that direction is to understand the type of data that can be collected in SDNs and how information can be learned from that data. In this work we describe a simple architecture deployed in an enterprise network that gathers traffic data using the OpenFlow protocol. We present the data-sets that can be obtained and show how several ML techniques can be applied to it for traffic classification. The results indicate that high accuracy classification can be obtained with the data-sets using supervised learning.

KW - Data Analysis

KW - Machine Learning

KW - Software defined Networks

KW - Traffic Classification

U2 - 10.1109/ICNP.2016.7785327

DO - 10.1109/ICNP.2016.7785327

M3 - Conference contribution

SN - 978-1-5090-3282-2

T3 - IEEE International Conference on Network Protocols Proceedings

BT - 2016 IEEE 24th International Conference on Network Protocols (ICNP)

PB - IEEE

CY - New York

Y2 - 8 November 2016 through 11 November 2016

ER -

Machine Learning in Software Defined Networks: Data collection and traffic classification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this