WOS3 – Cutting-Edge Techniques and Applications in Quantum Communication, Reconfigurable Transceivers, and AI-Driven Networking for the 6G-Era

Wednesday, 5 June 2024, 11:00-13:00, room Toucan 2

Session Chair:Daniel Kilper (Trinity College Dublin & CONNECT Centre, IE)

Evaluation Method and Case Study of Satellite Quantum Key Distribution for Terrestrial Networks
Javier Jordán-Parra (i2CAT Foundation, Spain); Marina Garcia-Romero (Fundació i2CAT, Spain); Sergi Figuerola (Chief Technology and Innovation Officer, i2CAT Foundationi, Spain); Joan Adria Ruiz-de-Azua (i2CAT Foundation, Spain); Josep Paradells (Universitat Politecnica de Catalunya, Spain)
Security is a major concern of digital society, and quantum key distribution (QKD) can contribute with an unconditional secure mechanism for symmetric key distribution. Satellites have the opportunity to overcome the range limit of quantum communications based on fiber networks. This paper presents a method for performance evaluation of QKD based on satellites, exemplified with a case study that considers small satellites (CubeSats) in low Earth orbits (LEO), to illustrate a flexible configuration of the quantum range extender use case. To the best of the authors’ knowledge, this is the first time that a system evaluation derived from orbital propagation data is conducted while also considering QKD with a finite key statistics approach. This evaluation aims to match with the shortness and variability of visibility intervals typical of LEO orbits. The results confirm the feasibility of proposed case study and show the impact of relevant systems and orbital parameters in the key generation performance, such as system characteristics, uplink or downlink configuration, satellite altitude and orbital inclination. The estimated performance is then scaled to a year along with some sensitivity scenarios. The presented results may guide the design of future QKD satellite mission proposals.

LR-FHSS-Sim: A Discrete-Event Simulator for LR-FHSS Networks
Jean Michel S Sant’Ana (University of Oulu, Finland); Arliones S Hoeller, Jr. (Federal Institute for Education, Science, and Technology of Santa Catarina, Brazil); Hirley Alves (University of Oulu, Finland); Richard Demo Souza (Federal University of Santa Catarina, Brazil)
This work presents the LR-FHSS-Sim, a free and open-source discrete-event simulator for LR-FHSS networks. We highlight the importance of network modeling for IoT coverage, especially when it is needed to capture dynamic network behaviors. Written in Python, we present the LR-FHSS-Sim main structure, procedures, and extensions. We discuss the importance of a modular code, which facilitates the creation of algorithmic strategies and signal-processing techniques for LR-FHSS networks. Moreover, we showcase how to achieve results when considering different packet generation traffic patterns and with a previously published extension. Finally, we discuss our thoughts on future implementations and what can be achieved with them.

Implementation of Reconfigurable 149Mbps TDC-Based PPM Transceiver
Pauls Eriks Sics, Nikolajs Tihomorskis and Sandis Migla (Riga Technical University, Latvia); Jakovs Ratners (Riga Technical University & SIA Eventech, Latvia); Viktors Kurtenoks and Arturs Aboltins (Riga Technical University, Latvia)
This research is devoted to developing the pulse position modulation (PPM) modem, which utilizes an extremely narrow 40 ps position width to achieve a theoretical bitrate above 160 Mbps. In this work, we present a PPM modulator, implemented using software-controlled digital delay lines (DDLs) and the demodulator based on the high precision event timer with streaming capabilities. The versatility of the proposed solution is achieved by relaying on software-defined radio (SDR) approach where the majority of modem functions are performed in software running on personal computer (PC) connected to the modem by USB3 interface. Unlike the traditional SDR, the proposed design relies on precise digital-to-time and time- to-digital conversion, which can cope with signals having up to 100 GHz bandwidth. Along with the design description, the use of Consultative Committee for Space Data Systems (CCSDS)-compliant Reed-Solomon error correcting code (ECC) for mitigating the timing errors is discussed. Results of laboratory testing of the PPM modem hardware prototype are presented and explained.

Multi-Layer Distributed Learning for Intelligent Transportation Systems in 6G Aerial-Ground Integrated Networks
David Naseh, Swapnil Shinde and Daniele Tarchi (University of Bologna, Italy)
Federated Learning (FL) is a widely used distributed learning (DL) method for intelligent transportation systems (ITS) in the upcoming era of 6G-enabled ITS. In this work, we present the concept of Generalized Federated Split Transfer Learning (GFSTL) as a highly efficient and secure distributed learning framework for resource-limited ITS applications. The proposed GFSTL solution performs better in terms of overall training latency and accuracy and is useful for enabling ITS services in Aerial-Ground Integrated Networks (AGIN). Through comprehensive simulations carried out in vehicular scenarios, our results validate the efficacy of GFSTL on multilayered DL using Road-Side Units (RSUs) and High-Altitude Platforms (HAPs) in AGIN, demonstrating significant improvements in addressing the demands of intelligent vehicular networks. Through the integration of advanced DL techniques and the use of HAPs, our proposed framework holds promise for paving the way for an intelligent and connected vehicular network in the future.

UAV-Assisted Enhanced Coverage and Capacity in Dynamic MU-mMIMO IoT Systems: A Deep Reinforcement Learning Approach
MohammadMahdi Ghadaksaz, Mobeen Mahmood and Tho Le-Ngoc (McGill University, Canada)
This study focuses on a multi-user massive multiple-input multiple-output (MU-mMIMO) system by incorporating an unmanned aerial vehicle (UAV) as a decode-and-forward (DF) relay between the base station (BS) and multiple Internet-of-Things (IoT) devices. Our primary objective is to maximize the overall achievable rate by introducing a novel framework that integrates joint hybrid beamforming (HBF) and UAV localization in dynamic MU-mMIMO IoT systems. Particularly, HBF stages for BS and UAV are designed by leveraging slow time-varying angular information, whereas a deep reinforcement learning (RL) algorithm, namely deep deterministic policy gradient (DDPG) with continuous action space, is developed to train the UAV for its deployment. By using a customized reward function, the RL agent learns an optimal UAV deployment policy capable of adapting to both static and dynamic environments. The illustrative results show that the proposed DDPG-based UAV deployment (DDPG-UD) can achieve approximately 99.5% of the sum-rate capacity achieved by PSO-based UAV deployment (PSO-UD), while requiring a significantly reduced runtime at approximately 68.50% of that needed by PSO-UD, offering an efficient solution in dynamic MU-mMIMO environments.

The Role of AI in 6G MAC
Alvaro Valcarce (Nokia Bell Labs, France); Petteri Kela (Nokia, Finland); Silvio Mandelli (Nokia Bell Labs, Germany); Harish Viswanathan (Nokia Bell Labs, USA)
The potential of Artificial Intelligence (AI) techniques, such as autoencoders, for customizing the wireless physical layer has been demonstrated in previous works. In the current paper, we move up the protocol stack and explore the frontiers of Machine Learning (ML) on the wireless Medium Access Control (MAC) layer. Unlike the Physical Layer (PHY), the MAC aggregates multiple independent features, which require a separate ML treatment. Considering this, this survey paper navigates recent research on AI-driven MAC functions such as resource allocation, random access, Adaptive Modulation and Coding (AMC), power control, protocol learning, Channel State Information (CSI) reporting, Hybrid Automatic Repeat Request (HARQ), and Multi-RAT Spectrum Sharing (MRSS).

Rate-Conforming Sub-Band Allocation for In-Factory Subnetworks: A Deep Neural Network Approach
Saeed Hakimi, Ramoni O Adeogun and Gilberto Berardinelli (Aalborg University, Denmark)
This paper focuses on the critical challenge of sub-band allocation for dense 6G In-factory subnetworks. We introduce a deep learning (DL) framework explicitly designed to effectively address the inherent optimization problem in sub-band assignment to subnetworks. To enhance the model’s training process, a novel strategy is implemented to handle integer optimization variables. The proposed approach aims at utilizing resources more efficiently by maximizing the number of rate-conforming subnetworks, serving as the key component of the loss function. Simulation results demonstrate that, across various classes of subnetworks, the proposed method achieves superior performance compared to State-of-the-Art (SoA) benchmarks with minimal computation time.

Go to Top