Congestion prevention mechanism based on Q-leaning for efficient routing in SDN

Seonhyeok Kim; Jaehyeok Son; Ashis Talukder; Choong Seon Hong

doi:10.1109/ICOIN.2016.7427100

Congestion prevention mechanism based on Q-leaning for efficient routing in SDN

Seonhyeok Kim, Jaehyeok Son, Ashis Talukder, Choong Seon Hong

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

40 Citations (Scopus)

Abstract

SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstra's Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.

Original language	English
Title of host publication	30th International Conference on Information Networking, ICOIN 2016
Publisher	IEEE Computer Society
Pages	124-128
Number of pages	5
ISBN (Electronic)	9781509017249
DOIs	https://doi.org/10.1109/ICOIN.2016.7427100
Publication status	Published - 7 Mar 2016
Event	30th International Conference on Information Networking, ICOIN 2016 - Kota Kinabalu, Malaysia Duration: 13 Jan 2016 → 15 Jan 2016

Publication series

Name	International Conference on Information Networking
Volume	2016-March
ISSN (Print)	1976-7684

Conference

Conference	30th International Conference on Information Networking, ICOIN 2016
Country/Territory	Malaysia
City	Kota Kinabalu
Period	13/01/16 → 15/01/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Controller
Q-learning
Software Defined Networking

Access to Document

10.1109/ICOIN.2016.7427100

Cite this

Kim, S., Son, J., Talukder, A., & Hong, C. S. (2016). Congestion prevention mechanism based on Q-leaning for efficient routing in SDN. In 30th International Conference on Information Networking, ICOIN 2016 (pp. 124-128). Article 7427100 (International Conference on Information Networking; Vol. 2016-March). IEEE Computer Society. https://doi.org/10.1109/ICOIN.2016.7427100

@inproceedings{8e35f64d5a8c4b4895c61ccb9debcb96,

title = "Congestion prevention mechanism based on Q-leaning for efficient routing in SDN",

abstract = "SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstra's Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.",

keywords = "Controller, Q-learning, Software Defined Networking",

author = "Seonhyeok Kim and Jaehyeok Son and Ashis Talukder and Hong, {Choong Seon}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 30th International Conference on Information Networking, ICOIN 2016 ; Conference date: 13-01-2016 Through 15-01-2016",

year = "2016",

month = mar,

day = "7",

doi = "10.1109/ICOIN.2016.7427100",

language = "English",

series = "International Conference on Information Networking",

publisher = "IEEE Computer Society",

pages = "124--128",

booktitle = "30th International Conference on Information Networking, ICOIN 2016",

address = "United States",

}

Kim, S, Son, J, Talukder, A & Hong, CS 2016, Congestion prevention mechanism based on Q-leaning for efficient routing in SDN. in 30th International Conference on Information Networking, ICOIN 2016., 7427100, International Conference on Information Networking, vol. 2016-March, IEEE Computer Society, pp. 124-128, 30th International Conference on Information Networking, ICOIN 2016, Kota Kinabalu, Malaysia, 13/01/16. https://doi.org/10.1109/ICOIN.2016.7427100

Congestion prevention mechanism based on Q-leaning for efficient routing in SDN. / Kim, Seonhyeok; Son, Jaehyeok; Talukder, Ashis et al.
30th International Conference on Information Networking, ICOIN 2016. IEEE Computer Society, 2016. p. 124-128 7427100 (International Conference on Information Networking; Vol. 2016-March).

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

TY - GEN

T1 - Congestion prevention mechanism based on Q-leaning for efficient routing in SDN

AU - Kim, Seonhyeok

AU - Son, Jaehyeok

AU - Talukder, Ashis

AU - Hong, Choong Seon

PY - 2016/3/7

Y1 - 2016/3/7

N2 - SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstra's Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.

AB - SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstra's Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.

KW - Controller

KW - Q-learning

KW - Software Defined Networking

UR - http://www.scopus.com/inward/record.url?scp=84963943834&partnerID=8YFLogxK

U2 - 10.1109/ICOIN.2016.7427100

DO - 10.1109/ICOIN.2016.7427100

M3 - Conference contribution

AN - SCOPUS:84963943834

T3 - International Conference on Information Networking

SP - 124

EP - 128

BT - 30th International Conference on Information Networking, ICOIN 2016

PB - IEEE Computer Society

T2 - 30th International Conference on Information Networking, ICOIN 2016

Y2 - 13 January 2016 through 15 January 2016

ER -

Congestion prevention mechanism based on Q-leaning for efficient routing in SDN

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this