The Role of Machine Learning in Fluid Network Control and Data Planes

Thursday, October 20, 2022 | 04:00 pm (CET) | Online via Zoom, please register here:

Prof. Dr. Christian Rothenberg | University of Campinas, Brazil

Abstract: As the network softwarization trend started by SDN and NFV keeps evolving, the hardware/software continuum becomes more relevant than ever, offering new offloading/acceleration opportunities at node and network-wide scales. This talk will review evolving transformations behind network softwarization with a special focus on network refactoring and offloading trends leading to “fluid networks planes”, characterized by multiple candidate options for the specific HW/SW embodiment and the location of chained network functions, from the edge to core, from one administrative provider to another, from programmable silicon to portable lightweight virtualized containers. The talk will overview concrete examples from the literature with a special focus on the role of Machine Learning to assist key (automated) decision-making steps.  Lastly, the talk will conclude with a glimpse on ongoing ML work applied to Youtube video QoE prediction in live 5G networks.



Bio: Christian Rothenberg is Associate Professor (tenure-track) and head of the Information & Networking Technologies Research & Innovation Group (INTRIG) at the School of Electrical and Computer Engineering (FEEC) of the University of Campinas (UNICAMP), where he received his Ph.D. in Electrical and Computer Engineering in 2010. From 2010 to 2013, he worked as Senior Research Scientist in the areas of IP systems and networking, leading SDN research at CPQD R&D Center in Telecommunications, Campinas, Brazil. He holds the Telecommunication Engineering degree from the Technical University of Madrid (ETSIT – UPM), Spain, and the M.Sc. (Dipl. Ing.) degree in Electrical Engineering and Information Technology from the Darmstadt University of Technology (TUD), Germany, 2006. Christian has contributed to 07 international patents, co-authored three books, and over 200 scientific publications, including top-tier scientific journals and networking conferences such as SIGCOMM and INFOCOM, altogether featuring 10 000+ citations (h-index: 30+, i10-index: 70+). 

Please follow and like us:
Posted in TEWI-Kolloquium | Kommentare deaktiviert für The Role of Machine Learning in Fluid Network Control and Data Planes
RSS
EMAIL