Enabling Software Defined Networking in High Criticality Networks

  • Joe Hollinghurst

Student thesis: Doctoral ThesisDoctor of Philosophy (PhD)

Abstract

High-criticality networking solutions are often dedicated, highly specialised, even bespoke in case of hard real-time guarantees. This is required to ensure (quasi) deterministic behaviour of the network services as seen by critical applications. However, dedicated networks incur significant expense, along with the inability to update the system efficiently and effectively. Software-Defined Networking (SDN) uses controllers to allow dynamic, user-controlled, on-demand configuration of the network. This provokes interesting questions on the applicability of SDN concepts and architectures in high-criticality networks.

Although SDN offers flexibility and programmability to the network infrastructure through the introduction of a controller, the controller introduces extra delay into the system. This is due to new flows querying the controller for instructions of how to route traffic. This becomes an increasing problem for large scale and delay sensitive networks such as those found in high-criticality infrastructure. The delay introduced can be minimised by optimal placement of the controller or decreased further by introducing additional controllers. Although the problem of optimal placement for multiple controllers is known to be NP hard, approximations can be used. The analysis of three different methods has been conducted and investigates the scalability, and how the accuracy of the methods varies with the complexity.

In the latter stage of the thesis the use of redundancy and coding is analysed with the aim to reduce latency and increase reliability within the network. The objective is to provide an analysis of the gains achievable through the use of redundant messages and coding. Both redundancy and coding increase the network load and hence the delay of each packet, but can reduce overall delay by exploiting independent randomness across multiple paths. Both the average delay minimisation and probabilistic guarantees on delay exceeding some tolerance threshold are considered.
Date of Award25 Sep 2018
Original languageEnglish
Awarding Institution
  • The University of Bristol
SupervisorA J Ganesh (Supervisor) & Timothy Baugé (Supervisor)

Cite this

'