News

Our paper on GNFC, a framework towards Network Function Cloudification has been recently accepted to IEEE NFV-SDN! In the paper, we reviewed and evaluated the current infrastructural limitations imposed by public cloud providers to deploy Network Function Virtualization (NFV) by tenants and present the design and implementation of GNFC, a cloud-based NFV framework that gives tenants the ability to transparently attach stateless, container-based network functions to their services hosted in public clouds. We evaluated the proposed system over three public cloud providers (Amazon EC2, Microsoft Azure and Google Compute Engine) and showed the effects on end-to-end latency and throughput using various instance types for NFV hosts. We are looking forward to the conference in San Francisco next month!

Our team has received a Best Paper Award at the 16th IEEE International Conference on High Performance Switching and Routing (HPSR) for the paper "Arbitrary Packet Matching in OpenFlow" in the beautiful city of Budapest (Hungary). The authors of the paper are Simon Jouet, Richard Cziva and Dimitrios Pezaros. In the paper, we analysed the matching abilities of Openflow and argued that a fully flexible match structure is superior to continuously extending the number of fields to match upon. We use Berkeley Packet Filters (BPF) for packet classification to provide a protocol-independent, flexible alternative to today’s OpenFlow fixed match fields. We have implemented a prototype system and evaluated the performance of the proposed match scheme, with a focus on the time it takes to execute and the memory required to store different match filter specifications. Our prototype implementation demonstrates that line-rate arbitrary packet classification can be achieved with complex BPF programs.

Our team has received a Best Paper Award at the 3rd IEEE International Conference on Cloud Networking (CloudNet) for the paper "SDN-based Virtual Machine Management for Cloud Data Centers" in the beautiful city of Luxembourgh (Luxembourgh). The authors of the paper are Richard Cziva, David Stapleton, Fung Po Tso and Dimitrios Pezaros. In this work, we presented a converged server-network resource management scheme by exploiting SDN. In particular, we exploited SDN to collect temportal network statistics and initiated Virtual Machine (VM) migrations from the SDN controller to consolidate VMs in a topology-aware way.