HIFFR: Hybrid Intelligent Fast Failure Recovery Framework for Enhanced Resilience in Software Defined Networks

Rehab Alawadh*, Poonam Yadav*, Hamed Ahmadi

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

Abstract

Deploying new optimised routing policies on routers in the event of link failure is difficult due to the strong coupling between the data and control planes and
the absence of topology information about the network.
Because of the distributed architecture of traditional Internet protocol networks, policies and routing rules are spread in a decentralised way, resulting in looping and congestion problems. Software-defined networking (SDN) enables centralised network programmability. As a result, data plane devices just focus on packet forwarding, leaving the control plane’s complexities to be managed by the controller. Thus, the controller centrally installs the policies and rules. Considering the controller’s knowledge of the global network architecture, central control enhances the flexibility of link failure identification and restoration. Therefore, this paper uses SDN architecture to enhance network resilience against link failures by introducing the
Hybrid Intelligent Fast Failure Recovery (HIFFR) framework, which aims to improve the speed and effectiveness of network failure recovery.
Original languageEnglish
Publication statusAccepted/In press - 30 May 2024

Keywords

  • Software-Defined Networking (SDN), Resilience, Link Failure, Routing Protocols, Graph Neural Network (GNN)

Cite this