Erol Gelenbe holds the “Dennis Gabor” professorship in Electrical and Electronic Engineering at Imperial College, London. After a childhood spent in Istanbul and Alexandria (Egypt), he graduated from Ankara College and the Middle East Technical University. He holds a PhD from Polytechnic Institute of New York, and a Doctor of Science from University Pierre et Marie Curie. He is a Fellow of ACM and IEEE and of the Royal Academy of Belgium, the Science Academies of Hungary, Poland and Turkey, the National Academy of Technologies of France, and of Academia Europaea.
His honours include the Commendatore al Merito of Italy and France’s Legion d’Honneur. He was awarded three Doctorate Honoris Causa degrees from the University of Rome Tor-Vergata, University of Liege (Belgium) and Bogazici University (Istanbul). At the INRIA institute and the University of Paris-Orsay, Erol created the team that developed the “Queueing Network Analysis Package”. He invented Diffusion Approximations for computer performance, derived transmission schemes to optimize the throughput of random access communications that are the basis of the well-known MAC and random-access protocols, and established check-pointing schemes for maximizing the reliability of data bases and high performance computers. The heart of ICT system performance methodology is based on queueing networks and their computationally efficient “product form” solution. Working at the University of Paris-Descartes and Duke University, he developed new product form queueing networks with negative customers and triggers known as G-networks or “Gelenbe Networks”, showing how to mathematically evaluate the performance of ICT systems that incorporate important control functions, such as removing overload or unwanted workload and moving work dynamically among servers. He also introduced a new spiked stochastic neural network model known as the Random Neural Network, developed its mathematical solution and learning algorithms, and applied it to both engineering and biological problems, and used it to design the Cognitive Packet Network routing algorithm. Today, we view systems such as Skype as a common means of human communication over the packet based Internet. In 1978, before packet networks were widely available, motivated by the need to improve voice telephony, Erol and a colleague from the company LMT made a major invention (patent filed in 1979 and awarded in 1982) regarding Voice Transmission over a multi-hop packet network, whose detailed architecture was described in a second patent filed by Erol and two colleagues on behalf of Thomson CSF (now Thales) in 1979 (also awarded in 1982).
Erol Gelenbe has experimentally demonstrated major advances in Machine Learning for Routing and Security in Intercontinental Networks and Software Defined Networks. He also works on optimising Energy Consumption in the Fog, and Security for IoT Networks through several H2020 projects. He has graduated over 81 PhD students, and mentored numerous post-doctoral fellows. The prizes he received include the 1996 Grand Prix France Telecom of the French Academy of Sciences, the 2008 ACM SIGMETRICS Life-Time Achievement Award, the 2013 Dennis Gabor Award of the Hungarian Academy of Sciences, and the 2017 Mustafa Prize for Information Sciences and Technologies.
Title: Machine Learning Approaches to Network Routing
In recent years, there has been increasing interest for new approaches to network routing, in particular through the use of machine learning to automate network functions so as to improve important metrics related to Quality of Service, Energy Consumption and Security in networks and the Cloud. This talk will review our work in this area based on the Cognitive Packet Network (CPN) and reinforcement learning. The principles of this approach that uses Random Neural Networks installed in Cognitive Routers will be outlined. Experimental results will be presented for optimising Quality of Service in dense clusters of routers and over long-range intercontinental networks. Means to implement some of these ideas using Software Defined Networks will also be discussed. Results presented will also address issues of energy savings and security enhancement through cognitive routing. This approach will also be illustrated for the Cloud-Network interface and the dynamic allocation of jobs in the Fog.
Mischa Dohler is full Professor in Wireless Communications at King’s College London, driving cross-disciplinary research and innovation in technology, sciences and arts. He is a Fellow of the IEEE, the Royal Academy of Engineering, the Royal Society of Arts (RSA), the Institution of Engineering and Technology (IET); and a Distinguished Member of Harvard Square Leaders Excellence. He is a serial entrepreneur; composer & pianist with 5 albums on Spotify/iTunes; and fluent in 6 languages. He acts as policy advisor on issues related to digital, skills and education. He has had ample coverage by national and international press and media.
He is a frequent keynote, panel and tutorial speaker, and has received numerous awards. He has pioneered several research fields, contributed to numerous wireless broadband, IoT/M2M and cyber security standards, holds a dozen patents, organized and chaired numerous conferences, was the Editor-in-Chief of two journals, has more than 200 highly-cited publications, and authored several books.
He was the Director of the Centre for Telecommunications Research at King’s from 2014-2018. He is the Cofounder of the Smart Cities pioneering company Worldsensing, where he was the CTO from 2008-2014. He also worked as a Senior Researcher at Orange/France Telecom from 2005-2008.
Geert Heijenk is a full professor in Wireless Networks and Mobility at the University of Twente, the Netherlands. He received his Ph.D. degree in 1995 from the same university. He has held a part-time position at KPN Research from 1989 until 1991. From 1995 until 2003, he was with Ericsson EuroLab Netherlands, leading a networking research group. From 2015 until 2018 he has been program director of the Computer Science and Internet Science & Technology bachelor and master programs of University of Twente. Geert Heijenk is steering committee member of IFIP WWIC and IEEE VNC. He has been a visiting researcher at the University of Pennsylvania, Philadelphia, and a visiting professor at the University of California, Irvine, and INRIA, Rocquencourt. His area of research is wireless networks and mobility. He is particularly interested in architectures, algorithms, and protocols for cellular, ad-hoc, sensor, and vehicular networks, and their application to cooperative autonomous driving.