GPTE: Efficient Graph Partitioning-based Traffic Engineering in Hybrid SDN/IP Networks

  • Huijun Dai
  • , Min Zhu
  • , Li Wang
  • , Jianlong Zhao
  • , Xiaolin Gui
  • , Guangyu Peng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Due to the lack of a centralized global view on the Traditional IP network, it may cause load imbalance or network congestion. Because of the high economical costs and technical conditions of the migration to full SDN, network operators prefer partial deployment of SDN-enabled devices in the IP network. An efficient graph partitioning-based TE (GPTE) in hybrid SDN/IP networks is proposed by considering the network topology, in which legacy devices and SDN-enabled devices co-exist. Firstly, GPTE models the partial SDN deployment as a Network Partitioning Problem solved by transforming the original network into its dual, which make the representation applicable to partitioning. Afterwards, GPTE formulates the TE as an Integer Linear Programming (ILP) by considering hybrid SDN/IP routing mechanism. Finally, through intensive experiments under different topologies, GPTE can achieve a significant improvements in terms of load balancing performance and can provide better TE capabilities.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages958-966
Number of pages9
ISBN (Electronic)9781728176499
DOIs
StatePublished - Dec 2020
Event22nd IEEE International Conference on High Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 - Virtual, Fiji, Fiji
Duration: 14 Dec 202016 Dec 2020

Publication series

NameProceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020

Conference

Conference22nd IEEE International Conference on High Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020
Country/TerritoryFiji
CityVirtual, Fiji
Period14/12/2016/12/20

Keywords

  • Graph Partitioning
  • Hybrid SDN/IP Network
  • SDN
  • TE

Fingerprint

Dive into the research topics of 'GPTE: Efficient Graph Partitioning-based Traffic Engineering in Hybrid SDN/IP Networks'. Together they form a unique fingerprint.

Cite this