Thursday 31 Oct 2019: Latency-Optimal vNF Orchestration at the Network Edge
Prof. Dimitrios Pezaros - University of Glasgow
Harrison 170 14:00-15:00
Abstract: Future networks are expected to support low-latency, context-aware and user-specific services in a highly flexible and efficient manner. One approach to support emerging use cases such as, e.g., VR and remote controlling of autonomous vehicles, is to introduce virtualized network functions (vNF)s at the edge of the network, placed in close proximity to the end users to reduce end-to-end latency, time-to-response, and unnecessary utilisation of the core.
In this talk, I will discuss the opportunities and challenges of virtualization at the network edge and present Glasgow Network Functions (GNF), a container-based NFV platform that runs and orchestrates lightweight container vNFs at the edge, saving core network utilization and providing latency-optimal function placement. I intend to go through the GNF architecture alongside some interesting use-cases of the platform to support, e.g., the roaming of network functions and their installation over unmanned vehicle topologies. Also, I will discuss the formulation of an edge vNF placement problem to minimise vNF-to-user latency over a (simulated) nation-wide backbone network using real-world ISP latency characteristics.
Bio: Dimitrios Pezaros is Professor of Computer Networks and founding director of the Networked Systems Research Laboratory (netlab) at the School of Computing Science, University of Glasgow. He is also a visiting professor at the University of Athens, Department of Informatics and Telecommunications. He has published widely in the areas of computer communications, network and service management, and resilience of future networked infrastructures, and has received significant funding for his research in the above areas from public funding agencies and the industry. Prof Pezaros holds BSc and PhD degrees in Computer Science from Lancaster University, he is a Chartered Engineer, and a senior member of the IEEE and the ACM.