IEEE.orgIEEE Xplore Digital Library IEEE Standards IEEE SpectrumMore Sites
T9: On Reinforcement and Deep Learning Performance in Wireless Communication - VTC2021-Spring Helsinki

T9 Title: On Reinforcement and Deep Learning Performance in Wireless Communication

Organizer: Haris Gacanin

Abstract: The fifth generation (5G) of wireless communications has led to many advancements in technologies such as large and distributed antenna arrays, ultra-dense networks, software-based networks and network virtualization. However, the need for a higher level of automation to establish hyper-low latency and hyper-high reliability for beyond 5G applications requires extensive research on machine learning with applications in wireless communications. Thereby, learning techniques will take a central stage in the sixth generation of wireless communications to cope up with the stringent application requirements. This tutorial discusses the practical limitations of reinforcement and deep learning methods in the context of resource management in nonstationary radio environment. Based on the practical limitations we carefully design and propose supervised, unsupervised, and reinforcement learning models to support rate maximization objective under user mobility. We discuss the effects of practical systems such as latency and reliability on the rate maximization with deep learning models. For common testing in the non-stationary environment, we present a generic dataset generation method to benchmark across different learning models versus traditional optimal resource management solutions. We aim to provide with motivation and data computational AI methodology of autonomous agents in the context of self-organization in real time. We elaborate on AI methods that unify sensing, perception, reasoning and learning. We discuss differences between training-based such as deep learning and training-free such as reinforcement learning AI methods for both matching and dynamic problems, respectively. Finally, we introduce the conceptual functions of autonomous agent with knowledge management with a practical case study illustrating the application and achievable performance of a mobile user.

Bio: Haris Gačanin received his Dipl.-Ing. degree in Electrical engineering from the University of Sarajevo in 2000. In 2005 and 2008, respectively, he received MSc and Ph.D. from Tohoku University in Japan. He was with Tohoku University from 2008 until 2010 first as Japan Society for the Promotion of Science (JSPS) postdoctoral fellow and later, as an Assistant Professor. He joined Alcatel-Lucent Bell (now Nokia Bell) in 2010 as a Physical-layer Expert and later as Department Head at Nokia Bell Labs. From 2020, he is a chair professor at RWTH Aachen University. His professional interests are related to broad areas of digital signal processing and artificial intelligence with applications in wireless communications. He has 200+ scientific publications (journals, conferences and patent applications) and invited/tutorial talks. He is a Distinguished Lecturer of IEEE Vehicular Technology Society and an Associate Editor of IEEE Communications Magazine, while he served as the editor of IEICE Transactions on Communications and IET Communications. He is a senior member of the Institute of Electrical and Electronics Engineers (IEEE) and the Institute of Electronics, Information and Communication Engineering (IEICE) and acted as a general chair and technical program committee member of various IEEE conferences. He is a recipient of several Nokia innovation awards, IEICE Communication System Study Group Best Paper Award (joint 2014, 2015, 2017), The 2013 Alcatel-Lucent Award of Excellence, the 2012 KDDI Foundation Research Award, the 2009 KDDI Foundation Research Grant Award, the 2008 JSPS Postdoctoral Fellowships for Foreign Researchers, the 2005 Active Research Award in Radio Communications, 2005 Vehicular Technology Conference (VTC 2005-Fall) Student Paper Award from IEEE VTS Japan Chapter and the 2004 Institute of IEICE Society Young Researcher Award. He was awarded by the Japanese Government (MEXT) Research Scholarship in 2002.