W5: Data Driven Optimization for 6G Wireless Networks
– AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning
Chien-Cheng Wu, Zheng-Hua Tan and Cedomir Stefanovic (Aalborg University)
– Channel Charting Assisted Beam Tracking
Parham Kazemi, Hanan Al-Tous ( Aalto University), Christoph Studer (ETH Zürich) and Olav Tirkkonen (Aalto University)
– Collision Resolution with Deep Reinforcement Learning for Random Access in Machine-Type Communication
Muhammad Jadoon, Adriano Pastore and Monica Navarro (Centre Tecnologic Telecomunicacions Catalunya)
– Control-Aware Scheduling Optimization of Industrial IoT
Pedro Maia de Sant Ana (Bosch), Beatriz Soret, Petar Popovski (Aalborg University) and Nikolaj Marchenko (Bosch)
– Heuristic Inspired Precoding for Millimeter-Wave MIMO Systems with Lens Antenna Subarrays
Sinasi Cetinkaya (University of South Florida) Liza Afeef (Istanbul Medipol University), Gokhan Mumcu and Hüseyin Arslan (University of South Florida)
– Intermodulation Interference Detection in 6G Networks: A Machine Learning Approach (Invited paper)
Faris B. Mismar (Bell Labs Consulting, USA)
– Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning (Invited paper)
Ju-Hyung Lee (Korea University), Hyowoon Seo ( Kwangwoon University), Jihong Park (Deakin University), Mehdi Bennis, (University of Oulu), Joongheon Kim and Young-Chai Ko ( Korea University)
– Scalable Joint Learning of Wireless Multiple-Access Policies and their Signaling
Mateus Pontes Mota, Alvaro Valcarce Rial ( Nokia Bell Labs France) and Jean-Marie Gorce (INSA Lyon)
– Swish-Driven GoogleNet for Intelligent Analog Beam Selection in Terahertz Beamspace MIMO
Hosein Zarini (Amirkabir University of Technology),Mohammad robatmilli (Sharif University of Technology), Mehdi Rasti (Amirkabir University of Technology), Sergey Andreev (Tampere University of Technology), and Pedro Henrique Juliano Nardeli (Lapeenranta University of Tehcnology)
– Three-Dimensional Scrambling Code for Multi-User MIMO Systems
Wei Gao, Xiaodong Ji, Xiqing Liu and Mugen Peng (Beijing University of Posts & Telecommunications)
– Attacker Identification in LoRaWAN Through Physical Channel Fingerprinting
Sobhi Alfayoumi and Xavier vilajosana (Open University of Catalonia)
Program Schedule: 19 June 2022
5 Welcome address 14:05 – 15:30 Technical session I: (Keynote 45 mint. and Q&A 10 mint. + 2 presentations, each 15 mint.)
15:30 – 16:00 Coffee break 16:00 – 17:30 Technical session II: (6 presentations, each 15 mint.)
Note: The time allocated for each presentation is 15 mints; 12 mint. for presentation and 3 mint. for Q&A.
Technical session I
– 14:05 – 15:00 Keynote Speech
– 15:00 – 15:15 Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning
– 15:15 – 15:30 Channel Charting Assisted Beam Tracking
Technical session II
– 16:00 – 16:15 Collision Resolution with Deep Reinforcement Learning for Random Access in Machine-Type Communication
– 16:15 – 16:30 Swish-Driven Google Net for Intelligent Analog Beam Selection in Terahertz Beam space MIMO
– 16:30 – 16:45 Heuristic Inspired Precoding for Millimeter-Wave MIMO Systems with Lens Antenna Subarrays
– 16:45 – 17:00 Attacker Identification in LoRaWAN Through Physical Channel Fingerprinting
– 17:00 – 17:15 Scalable Joint Learning of Wireless Multiple-Access Policies and their Signaling
– 17:15 – 17:30 Three-Dimensional Scrambling Code for Multi-User MIMO Systems
Keynote Speaker: Wei Yu, University of Toronto
Title: Learn to Optimize for Wireless Communications
Abstract: Machine learning will have an important role to play in the optimization of future-generation physical-layer wireless communication system design for the following two reasons. First, traditional wireless communication design always relies on the channel model, but models are inherently only an approximation to the reality. In wireless environments where the models are complex and the channels are costly to estimate, a machine learning based approach that performs system-level optimization without explicit channel estimation can significantly outperform the traditional channel estimation based approaches. Second, modern wireless communication design often involves optimization problems that are high-dimensional, nonconvex, and difficult to solve efficiently. By exploring the availability of training data, a neural network may be able to learn the solution of an optimization problem directly. This can lead to a more efficient way to solve nonconvex optimization problems. In this talk, I will use examples from optimizing a reconfigurable intelligent surface (RIS) system, precoding for a massive multiple-input multiple-output (MIMO) system, and active sensing for mmWave channel initial alignment to illustrate the benefit of learning-based physical-layer communication system design. We illustrate that matching the neural network architecture to the problem structure is crucial for the success of learning based approaches.
Bio: Wei Yu received the B.A.Sc. degree in Computer Engineering and Mathematics from the University of Waterloo, Canada, and M.S. and Ph.D. degrees in Electrical Engineering from Stanford University, U.S.A. He has been with the Electrical and Computer Engineering Department at the University of Toronto since 2002, where he is now Professor and holds a Canada Research Chair in Information Theory and Wireless Communications. Prof. Wei Yu is a Fellow of IEEE, a Fellow of the Canadian Academy of Engineering, and a member of the College of New Scholars, Artists and Scientists of the Royal Society of Canada. He received the Steacie Memorial Fellowship in 2015, the IEEE Marconi Prize Paper Award in Wireless Communications in 2019, the IEEE Communications Society Award for Advances in Communication in 2019, the IEEE Signal Processing Society Best Paper Award in 2008, 2017 and 2021, the Journal of Communications and Networks Best Paper Award in 2017, and the IEEE Communications Society Best Tutorial Paper Award in 2015. Prof. Wei Yu was an IEEE Communications Society Distinguished Lecturer in 2015-16. He served as the Chair of the Signal Processing for Communications and Networking Technical Committee of the IEEE Signal Processing Society in 2017-18. Prof. Wei Yu was the President of the IEEE Information Theory Society in 2021.
Bio: Hanan Al-Tous (Senior Member, IEEE) is a research fellow at Aalto university. Her research interests include cooperative communications, energy harvested sensor networks, resource allocation for wireless communications, game theory, compressive sensing and machine learning.
Bio: Cedomir Stefanovic received the Diploma Ing., Mr.-Ing., and Ph.D. degrees from the University of Novi Sad, Serbia. He is currently a Professor with the Department of Electronic Systems, Aalborg University, where he leads the Edge Computing and Networking Group. He is a principal researcher on a number of European projects related to IoT, 5G, and mission-critical communications. He has coauthored more than 100 peer-reviewed publications. His research interests include communication theory and wireless communications. He serves as an editor for the IEEE Internet of Things Journal.
Bio: Sergey received M.Sc. degree in wireless systems & networks (radio frequency engineering) from Russian Technological University in 2015. Same year he joined Huawei Technologies as a senior research engineer. Where he worked on topics of hybrid beamforming, antenna array calibration, neural networks for digital pre-distortion and Bayesian source separation for intermodulation correction. In September of 2019 he joined Ericsson Research (funded by Horizon 2020 Marie Skłodowska-Curie project) to work on topic of “Machine learning for real-time radio signal processing”. His current research interests are in topics of Bayesian optimisation and Gaussian processes for system identification and wireless networks.
Bio: Olav Tirkkonen: (Senior Member, IEEE) is associate professor in communication theory at the Department of Communications and Networking in Aalto University, Finland. He has published some 300 papers, is the inventor of some 85 families of patents and patent applications and is coauthor of the book “Multiantenna transceiver techniques for 3G and beyond”. His current research interests are in coding for random access and quantization, quantum computation, and machine learning for cellular networks. He is an associate editor of IEEE Transactions on Wireless Communication.
Bio: Hugo Tullberg is a Principal Researcher at Research Area Radio, Ericsson Research, Stockholm, where he works with Beyond-5G/6G communication systems. His research interests include communication and information theory, machine learning and artificial intelligence with applications to lower protocol layers, and network reliability and security. He is a member of the Technical Committee of Signal Processing for Communications and Networking within the IEEE Signal Processing Society.
Alvaro Valcarce Rial
Bio: Alvaro Valcarce (Senior Member, IEEE) is a research engineer at Nokia Bell Labs, France, where he focuses on the application of reinforcement learning to L2 and L3 problems for the development of beyond 5G technologies. His background is on LTE cellular networks, small-cells, computational electromagnetics, optimization algorithms and machine learning. He also has experience on the usage of satellite & cellular systems in aeronautical environments.