Thursday, 8 June 2023, 16:00-17:30, Room R2

Session Chair: Anna Brunstrom (Karlstad University, Sweden)

Copa-D: Delay Consistent Copa for Dynamic Cellular Networks
Habtegebreil Haile and Karl-Johan Grinnemo (Karlstad University, Sweden); Simone Ferlin (Red Hat and Karlstad University, Sweden); Per Hurtig and Anna Brunstrom (Karlstad University, Sweden)
The lack of consideration for application delay requirements in standard loss-based congestion control algorithms (CCAs) has motivated the proposal of several alternative CCAs. Among these new CCAs, Copa is one of the promising few CCAs that have attracted attention from both academia and industry. The delay performance of Copa is governed by a mostly static latency-throughput tradeoff parameter, δ. However, a static δ parameter makes it difficult for Copa to achieve consistent delay and throughput over a range of bottleneck bandwidths. In particular, the coexistence of 4G and 5G networks and the wide range of bandwidths experienced in NG-RANs can result in inconsistent CCA performance. To this end, we propose CopaD, a modification to Copa that dynamically tunes δ to achieve a consistent delay performance. We evaluate the modification over fixed, 4G, and 5G emulated bottlenecks. Our results show that Copa-D achieves consistent delay with minimal impact on throughput in fixed capacity bottlenecks. Copa-D also allows a more intuitive way of specifying the latency-throughput tradeoff and achieves more accurate and predictable delay in variable cellular bottlenecks.

Photonic-Accelerated AI for Cybersecurity in Sustainable 6G Networks
Emilio Paolini (Scuola Superiore Sant’Anna & CNR, Italy); Nicola Andriolli (National Research Council of Italy, Italy); Luca Maggiani (SmaRTy Italia SRL, Italy); Luca Valcarenghi (Scuola Superiore Sant’Anna, Italy)
The sixth generation (6G) of mobile communications, expected to be deployed around the year 2030, is predicted to be characterized by ubiquitous connected intelligence. With Artificial Intelligence (AI) operations being deployed in every aspect of future network infrastructure, network security will also evolve from current solutions to intelligent architectures. To meet the massive amount of operations computed by AI models, photonic hardware can be exploited, delivering higher processing speed and computing density and lower power consumption with respect to electronic counterparts. In this paper, we propose a photonic-based Convolutional Neural Network (CNN) solution able to work on real-time traffic, capable of identifying Denial of Service (DoS) Hulk attacks with 99.73 mean F1-score when exploiting 4 bits. We also compared photonic accelerators with their electronic counterparts, showing limited F1-score degradation, especially in the 4 and 8 bit scenarios.

Orchestration Procedures for the Network Intelligence Stratum in 6G Networks
Livia Elena Chatzieleftheriou (IMDEA Networks Institute, Spain); Marco Gramaglia (Universidad Carlos III de Madrid, Spain); Miguel Camelo (University of Antwerp – imec, Belgium); Andres Garcia-Saavedra (NEC Labs Europe, Germany); Evangelos Kosmatos (WINGS ICT Solutions, Greece); Michele Gucciardo (IMDEA Networks Institute, Spain); Paola Soto (Universiteit Antwerpen – imec, Belgium & Universidad de Antioquia, Colombia); George Iosifidis (Delft University of Technology, The Netherlands); Lidia Fuentes (University of Malaga, Spain); Ginés Garcia-Aviles (i2CAT, Spain); Andra Lutu (Telefónica Research, Spain); Gabriele Baldoni (ADLINK Technology, France); Marco Fiore (IMDEA Networks Institute, Spain)
The quest for autonomous mobile networks introduces the need for fully native support for Network Intelligence (NI) algorithms, typically based on Artificial Intelligence tools like Machine Learning, which shall be gathered into a NI stratum. The NI stratum is responsible for the full automation of the NI operation in the network, including the management of the life-cycle of NI algorithms, in a way that is synergic with traditional network management and orchestration framework. In this regard, the NI stratum must accommodate the unique requirements of NI algorithms, which differ from the ones of, e.g., virtual network functions, and thus plays a critical role in the native integration of NI into current network architectures. In this paper, we leverage the recently proposed concept of Network Intelligence Orchestrator (NIO) to (i) define the specific requirements of NI algorithms, and (ii) discuss the procedures that shall be supported by an NIO sitting in the NI stratum to effectively manage NI algorithms. We then (iii) introduce a reference implementation of the NIO defined above using cloudnative open-source tools.

Age of Information in Network Coded Multicast Networks
Alper Kose (Boğaziçi University, Turkey); Mutlu Koca and Emin Anarim (Bogazici University, Turkey)
We consider the timeliness in delivery of update packets in a two-way relay network with or without employing network coding in multicast transmissions where Age of Information (AoI) is adopted to quantify the timeliness of updates. The expressions for peak and average expected AoIs are analytically derived for both uncoded and network coded transmissions. The effect of network coding on AoI and asymptotic behaviors of the AoI derivations are evaluated. The behavioral analyses of various network parameters are investigated and the effect of each parameter to the AoI difference between coded and uncoded has been derived. Our analysis suggests that the utilization of network coding for multicast transmissions can result in substantial improvements in terms of AoI, with the exception of scenarios in which sensors possess extremely limited computational capabilities.

Study on Handover Techniques for Satellite-To-Ground Links in High and Low Interference Regimes
Abhipshito Bhattacharya (RWTH Aachen University, Germany); Marina Petrova (RWTH Aachen University & KTH Royal Institute of Technolgy, Germany)
The launch of private non-geostationary satellite orbit (NGSO) satellite constellations in recent years such as SpaceX’s Starlink and Amazon’s Kuiper has put satellite communications in focus as a potential provider of high-throughput broadband services. It is expected that satellite networks will be integrated into future 6G networks, and fortify global connectivity in the upcoming years. One major challenge with these NGSO networks, is the mobility-management. Due to the inherent high speed mobility of the satellites, the coverage area from a particular satellite to the ground is constantly moving, so frequent handovers are needed to sustain satelliteto-ground links. In this paper, we implement and evaluate the impact of three satellite-to-ground-link handover (HO) strategies, namely Closest Satellite, Max-Visibility and CINR-Threshold on the satellite-to-ground link performance in terms of spectrum efficiency and HO rate under high and low interference regimes. We consider three prominent private LEO mega-constellations namely SpaceX Gen2, Kuiper and OneWebLEO; and one MEO constellation namely Mangata, all operating in the Kaband. Through extensive simulations we show that the CINRThreshold strategy gives the best trade-off between throughput and HO rate, irrespective of the constellation design, level of interference and location./p>

Go to Top