Traffic engineering framework with machine learning based meta-layer in software-defined networks

Yanjun Li, Xiaobo Li, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Software-defined networks is an emerging architecture that separates the control plane and data plane. This paradigm enables flexible network resource allocations for traffic engineering, which aims to gain better network capacity and improved delay and loss performance. As we know, many heuristic algorithms have been developed to solve the dynamic routing problem. Whereas they lead to a high computational time cost, which results in a crucial problem whether such a heuristic approach to this NP-complete problem is of any use in practice. This paper proposes a framework with supervised machine learning based meta-layer to solve the dynamic routing problem in real time. We construct multiple machine learning modules in meta-layer, whose training set is consist of heuristic algorithm's input and its corresponding output. We show that after training process, the meta-layer will give heuristic-like results directly and independently, substituting for the time-consuming heuristic algorithm. We demonstrate, by analysis and simulation, our framework effectively enhance the network performance. Finally, the meta-layer architecture is quite universal and can be extended in numerous ways to accommodate a variety of traffic engineering scenarios in the network.

Original languageEnglish
Title of host publicationProceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages121-125
Number of pages5
ISBN (Print)9781479947362
DOIs
Publication statusPublished - 2014 Dec 30
Event2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014 - Beijing, China
Duration: 2014 Sep 192014 Sep 21

Other

Other2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014
CountryChina
CityBeijing
Period14/9/1914/9/21

Fingerprint

Heuristic algorithms
Learning systems
Network performance
Resource allocation
Computational complexity
Costs

Keywords

  • machine learning
  • meta-layer
  • routing
  • software-defined networks
  • traffic engineering

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Li, Y., Li, X., & Yoshie, O. (2014). Traffic engineering framework with machine learning based meta-layer in software-defined networks. In Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014 (pp. 121-125). [7000278] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICNIDC.2014.7000278

Traffic engineering framework with machine learning based meta-layer in software-defined networks. / Li, Yanjun; Li, Xiaobo; Yoshie, Osamu.

Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 121-125 7000278.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, Y, Li, X & Yoshie, O 2014, Traffic engineering framework with machine learning based meta-layer in software-defined networks. in Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014., 7000278, Institute of Electrical and Electronics Engineers Inc., pp. 121-125, 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014, Beijing, China, 14/9/19. https://doi.org/10.1109/ICNIDC.2014.7000278
Li Y, Li X, Yoshie O. Traffic engineering framework with machine learning based meta-layer in software-defined networks. In Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 121-125. 7000278 https://doi.org/10.1109/ICNIDC.2014.7000278
Li, Yanjun ; Li, Xiaobo ; Yoshie, Osamu. / Traffic engineering framework with machine learning based meta-layer in software-defined networks. Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 121-125
@inproceedings{3257151133004ed99ee82fb4b8f6135d,
title = "Traffic engineering framework with machine learning based meta-layer in software-defined networks",
abstract = "Software-defined networks is an emerging architecture that separates the control plane and data plane. This paradigm enables flexible network resource allocations for traffic engineering, which aims to gain better network capacity and improved delay and loss performance. As we know, many heuristic algorithms have been developed to solve the dynamic routing problem. Whereas they lead to a high computational time cost, which results in a crucial problem whether such a heuristic approach to this NP-complete problem is of any use in practice. This paper proposes a framework with supervised machine learning based meta-layer to solve the dynamic routing problem in real time. We construct multiple machine learning modules in meta-layer, whose training set is consist of heuristic algorithm's input and its corresponding output. We show that after training process, the meta-layer will give heuristic-like results directly and independently, substituting for the time-consuming heuristic algorithm. We demonstrate, by analysis and simulation, our framework effectively enhance the network performance. Finally, the meta-layer architecture is quite universal and can be extended in numerous ways to accommodate a variety of traffic engineering scenarios in the network.",
keywords = "machine learning, meta-layer, routing, software-defined networks, traffic engineering",
author = "Yanjun Li and Xiaobo Li and Osamu Yoshie",
year = "2014",
month = "12",
day = "30",
doi = "10.1109/ICNIDC.2014.7000278",
language = "English",
isbn = "9781479947362",
pages = "121--125",
booktitle = "Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Traffic engineering framework with machine learning based meta-layer in software-defined networks

AU - Li, Yanjun

AU - Li, Xiaobo

AU - Yoshie, Osamu

PY - 2014/12/30

Y1 - 2014/12/30

N2 - Software-defined networks is an emerging architecture that separates the control plane and data plane. This paradigm enables flexible network resource allocations for traffic engineering, which aims to gain better network capacity and improved delay and loss performance. As we know, many heuristic algorithms have been developed to solve the dynamic routing problem. Whereas they lead to a high computational time cost, which results in a crucial problem whether such a heuristic approach to this NP-complete problem is of any use in practice. This paper proposes a framework with supervised machine learning based meta-layer to solve the dynamic routing problem in real time. We construct multiple machine learning modules in meta-layer, whose training set is consist of heuristic algorithm's input and its corresponding output. We show that after training process, the meta-layer will give heuristic-like results directly and independently, substituting for the time-consuming heuristic algorithm. We demonstrate, by analysis and simulation, our framework effectively enhance the network performance. Finally, the meta-layer architecture is quite universal and can be extended in numerous ways to accommodate a variety of traffic engineering scenarios in the network.

AB - Software-defined networks is an emerging architecture that separates the control plane and data plane. This paradigm enables flexible network resource allocations for traffic engineering, which aims to gain better network capacity and improved delay and loss performance. As we know, many heuristic algorithms have been developed to solve the dynamic routing problem. Whereas they lead to a high computational time cost, which results in a crucial problem whether such a heuristic approach to this NP-complete problem is of any use in practice. This paper proposes a framework with supervised machine learning based meta-layer to solve the dynamic routing problem in real time. We construct multiple machine learning modules in meta-layer, whose training set is consist of heuristic algorithm's input and its corresponding output. We show that after training process, the meta-layer will give heuristic-like results directly and independently, substituting for the time-consuming heuristic algorithm. We demonstrate, by analysis and simulation, our framework effectively enhance the network performance. Finally, the meta-layer architecture is quite universal and can be extended in numerous ways to accommodate a variety of traffic engineering scenarios in the network.

KW - machine learning

KW - meta-layer

KW - routing

KW - software-defined networks

KW - traffic engineering

UR - http://www.scopus.com/inward/record.url?scp=84929415083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929415083&partnerID=8YFLogxK

U2 - 10.1109/ICNIDC.2014.7000278

DO - 10.1109/ICNIDC.2014.7000278

M3 - Conference contribution

AN - SCOPUS:84929415083

SN - 9781479947362

SP - 121

EP - 125

BT - Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content, IEEE IC-NIDC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -