Maintaining the Network Performance of Software-Defined WANs With Efficient Critical Routing

Zehua Guo*, Changlin Li, Yang Li, Songshi Dou, Bida Zhang, Weichao Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Software-Defined Networking (SDN) brings new opportunities to improve network performance of Wide Area Networks (WANs). To enhance the control plane's processing ability, a Software-Defined Wide Area Network (SD-WAN) usually employs multiple SDN controllers to control a large scale network. The controllers keep a consistent network state with each other via the controller synchronization. A controller synchronization usually involves all controllers, and the network cannot operate until the synchronization is done. Therefore, existing controller synchronization schemes could affect network performance and increase high resource consumption, thus increasing the complexity of running the SD-WAN. In this paper, we propose ThresHold-based critical flOw Routing (THOR) to maintain good load balancing performance of the network. THOR identifies and reroutes critical flows in single domains to achieve the network requirement without affecting other domains. If the rerouting does not satisfy the performance threshold, we generate and reroute several traversing flows among several domains to improve network performance. Simulation results show that THOR achieves 87% of the load balancing performance and reduces the number of synchronizations by approximately 80%, compared with the existing optimal flow routing.

Original languageEnglish
Pages (from-to)2240-2252
Number of pages13
JournalIEEE Transactions on Network and Service Management
Volume21
Issue number2
DOIs
Publication statusPublished - 1 Apr 2024

Keywords

  • Software-defined networking
  • critical flow
  • routing
  • synchronization

Fingerprint

Dive into the research topics of 'Maintaining the Network Performance of Software-Defined WANs With Efficient Critical Routing'. Together they form a unique fingerprint.

Cite this