...
- Networks are in a constant state of change. How to update them consistently?
Change the network topology on the fly: lasers, mirrors, antennas
- Programmable matter
Bitcoin from a networking perspective
Distributed systems with cheap machines
What to do when your network fails? Fast local failover mechanisms
Distributed proofs
Online exploration and evacuation
Predictability of Virtual Network Control for Software-Defined Networks
Your own project idea related to networks and communication technologies
Networks are in a constant state of change. How to update them consistently? |
---|
Since the recent rise of Software-Defined Networking, computer networks have become programmable. Hence, network operators can change, e.g., routing behavior on the fly, all from the (comfortable) viewpoint of a central point of control. Such techniques allow to optimize the network's performance under different workloads and use-cases. However, a computer network consists of many distributed components, sometimes even on the other side of the globe. Some parts of them can take longer to update their behavior, some might get conflicting commands – which can lead to inconsistent behavior, causing, e.g., congestion, packet drops, etc. In this thesis, you will investigate causes and solutions to such inconsistencies. Possible research directions include:
If you are interested, contact us and we can discuss possible directions for your thesis/project. To get a feeling for some past research on these topics (non-exhaustive), please feel free to look at the following:
|
This topic is available at all levels. |
...
Predictability of Virtual Network Control for Software-Defined Networks |
---|
Network Virtualization (NV) and Software-Defined networking (SDN) are expected to play a major role in future communication networks. With network virtualization, services can run in an isolated manner within their own virtual networks. Software-defined networking is expected to introduce the programmability gain for each virtual network. In order to realize such setting, however, an additional entity is needed: the SDN network hypervisor realizing the functionalities of virtualization for software-defined networks. Interestingly, less is known about the potential sources of unpredictability of today's network hypervisor solutions. This stands in stark contrast to the overall goal to achieve programmable virtual networks with predictable control. The aim of this thesis is to investigate the dierent mechanisms to provide virtual software defined networks and potential possibilities with particular focus on OnVisor. OnVisor has been recently published as a virtualization add on of the carrier grade software-defined networking controller ONOS. Furthermore, OnVisor performance should be compared with FlowVisor and OpenVirtex | hypervisors that are a little long in the tooth. This measurement study should identify scenarios in which interference among multi-tenant setups in virtualized SDN networks can happen. Different control plane messages and network topology settings should be investigated to reveal the cases when interference happens. Moreover by looking at the measurement data, the power of Machine Learning should be used to answer the overall question: is the performance of multi-tenant SDN environments truly predictable? First steps
What we offer
Expected knowledge
Keywords: Software Dened Networking, Network Virtualization, Machine Learning, OpenFlow, Predictability References
|
This topic is available at all levels. |
Should you have your own idea for a potential thesis which you think might fit the research interests of our group, do not hesitate to contact us directly. |
This topic is available at all levels. |
...