Balancing flow table occupancy and link utilization in software-defined networks

Zehua Guo, Yang Xu, Ruoyan Liu, Andrey Gushchin, Kuan yin Chen, Anwar Walid, H. Jonathan Chao

Research output: Contribution to journalArticle

Abstract

Software-Defined Networking (SDN) employs a centralized control with a global network view and provides great opportunities to improve network performance. However, due to the limitation of flow-table space at the switches and unbalanced traffic allocation on links, an SDN may suffer from flow-table overflow and inefficient bandwidth allocation among flows, increasing the controller's burden and degrading network performance. In this paper, we present a dynamic routing scheme named DIFF that differentiates flows based on their impact on network resource and adaptively selects routing paths for them to mitigate the problems of flow-table overflow and inefficient bandwidth allocation. DIFF pre-generates a set of paths for each pair of source–destination edge switches and intelligently selects the paths from the pre-generated path-sets for new flows with an objective to balance flow-table utilizations. It adaptively reroutes some elephant flows to achieve maximum throughput under the rule of max–min fair bandwidth allocation. Simulation results show that DIFF simultaneously balances the flow-table and link utilizations, reduces the controller's workload and packet delay, while increasing network throughput, compared with baseline schemes.

Original languageEnglish (US)
Pages (from-to)213-223
Number of pages11
JournalFuture Generation Computer Systems
Volume89
DOIs
StatePublished - Dec 1 2018

Fingerprint

Frequency allocation
Network performance
Switches
Throughput
Controllers
Telecommunication traffic
Telecommunication links
Software defined networking

Keywords

  • Flow-table overflow
  • Max–min fairness
  • OpenFlow
  • Routing
  • Software-defined networking

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Balancing flow table occupancy and link utilization in software-defined networks. / Guo, Zehua; Xu, Yang; Liu, Ruoyan; Gushchin, Andrey; Chen, Kuan yin; Walid, Anwar; Chao, H. Jonathan.

In: Future Generation Computer Systems, Vol. 89, 01.12.2018, p. 213-223.

Research output: Contribution to journalArticle

Guo, Zehua ; Xu, Yang ; Liu, Ruoyan ; Gushchin, Andrey ; Chen, Kuan yin ; Walid, Anwar ; Chao, H. Jonathan. / Balancing flow table occupancy and link utilization in software-defined networks. In: Future Generation Computer Systems. 2018 ; Vol. 89. pp. 213-223.
@article{a5b624db3e6d4ee787b75efc461220e3,
title = "Balancing flow table occupancy and link utilization in software-defined networks",
abstract = "Software-Defined Networking (SDN) employs a centralized control with a global network view and provides great opportunities to improve network performance. However, due to the limitation of flow-table space at the switches and unbalanced traffic allocation on links, an SDN may suffer from flow-table overflow and inefficient bandwidth allocation among flows, increasing the controller's burden and degrading network performance. In this paper, we present a dynamic routing scheme named DIFF that differentiates flows based on their impact on network resource and adaptively selects routing paths for them to mitigate the problems of flow-table overflow and inefficient bandwidth allocation. DIFF pre-generates a set of paths for each pair of source–destination edge switches and intelligently selects the paths from the pre-generated path-sets for new flows with an objective to balance flow-table utilizations. It adaptively reroutes some elephant flows to achieve maximum throughput under the rule of max–min fair bandwidth allocation. Simulation results show that DIFF simultaneously balances the flow-table and link utilizations, reduces the controller's workload and packet delay, while increasing network throughput, compared with baseline schemes.",
keywords = "Flow-table overflow, Max–min fairness, OpenFlow, Routing, Software-defined networking",
author = "Zehua Guo and Yang Xu and Ruoyan Liu and Andrey Gushchin and Chen, {Kuan yin} and Anwar Walid and Chao, {H. Jonathan}",
year = "2018",
month = "12",
day = "1",
doi = "10.1016/j.future.2018.06.011",
language = "English (US)",
volume = "89",
pages = "213--223",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Balancing flow table occupancy and link utilization in software-defined networks

AU - Guo, Zehua

AU - Xu, Yang

AU - Liu, Ruoyan

AU - Gushchin, Andrey

AU - Chen, Kuan yin

AU - Walid, Anwar

AU - Chao, H. Jonathan

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Software-Defined Networking (SDN) employs a centralized control with a global network view and provides great opportunities to improve network performance. However, due to the limitation of flow-table space at the switches and unbalanced traffic allocation on links, an SDN may suffer from flow-table overflow and inefficient bandwidth allocation among flows, increasing the controller's burden and degrading network performance. In this paper, we present a dynamic routing scheme named DIFF that differentiates flows based on their impact on network resource and adaptively selects routing paths for them to mitigate the problems of flow-table overflow and inefficient bandwidth allocation. DIFF pre-generates a set of paths for each pair of source–destination edge switches and intelligently selects the paths from the pre-generated path-sets for new flows with an objective to balance flow-table utilizations. It adaptively reroutes some elephant flows to achieve maximum throughput under the rule of max–min fair bandwidth allocation. Simulation results show that DIFF simultaneously balances the flow-table and link utilizations, reduces the controller's workload and packet delay, while increasing network throughput, compared with baseline schemes.

AB - Software-Defined Networking (SDN) employs a centralized control with a global network view and provides great opportunities to improve network performance. However, due to the limitation of flow-table space at the switches and unbalanced traffic allocation on links, an SDN may suffer from flow-table overflow and inefficient bandwidth allocation among flows, increasing the controller's burden and degrading network performance. In this paper, we present a dynamic routing scheme named DIFF that differentiates flows based on their impact on network resource and adaptively selects routing paths for them to mitigate the problems of flow-table overflow and inefficient bandwidth allocation. DIFF pre-generates a set of paths for each pair of source–destination edge switches and intelligently selects the paths from the pre-generated path-sets for new flows with an objective to balance flow-table utilizations. It adaptively reroutes some elephant flows to achieve maximum throughput under the rule of max–min fair bandwidth allocation. Simulation results show that DIFF simultaneously balances the flow-table and link utilizations, reduces the controller's workload and packet delay, while increasing network throughput, compared with baseline schemes.

KW - Flow-table overflow

KW - Max–min fairness

KW - OpenFlow

KW - Routing

KW - Software-defined networking

UR - http://www.scopus.com/inward/record.url?scp=85050098847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050098847&partnerID=8YFLogxK

U2 - 10.1016/j.future.2018.06.011

DO - 10.1016/j.future.2018.06.011

M3 - Article

AN - SCOPUS:85050098847

VL - 89

SP - 213

EP - 223

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

ER -