AI & Neuromorphic SatCom | Dr. Jorge Querol

When 5G NTN Meets GNSS: Tracking GNSS Signals under Overlaid 5G Waveforms

Sun, 24 May 2026 00:00:00 +0000

Abstract & Overview

Global Navigation Satellite Systems (GNSS) provide the backbone of Positioning, Navigation, and Timing (PNT) but remain vulnerable to interference. Low Earth Orbit (LEO) constellations within Fifth-Generation (5G) Non-Terrestrial Networks (NTN) can enhance resilience by jointly supporting communication and navigation. This paper presents the first quantitative analysis of GNSS tracking and navigation message demodulation under a hybrid waveform where a low-power Direct-Sequence Spread Spectrum (DSSS) component is overlaid on an Orthogonal Frequency-Division Multiplexing (OFDM) 5G downlink. We evaluate a minimally modified GNSS receiver that tracks a legacy Global Positioning System (GPS) L1 Coarse/Acquisition (C/A) overlay aligned with 5G frames while treating the 5G waveform as structured interference. Using Monte Carlo simulations under realistic LEO Doppler dynamics, we analyze the Bit Error Rate (BER) of GPS L1 C/A navigation bits and the subframe decoding probability versus Signalto- Interference-plus-Noise Ratio (SINR) for multiple Signalto- Interference Ratios (SIR) and dynamic classes. Results show reliable demodulation across wide SINR ranges for low and medium dynamics, whereas high dynamics impose strict lock limits. These findings confirm the feasibility of Joint Communication and Positioning (JCAP) using a near-legacy GNSS chipset with minimal receiver modifications.

Publication Metadata

Authors: Idir Edjekouane, Alejandro Gonzalez-Garrido, Jorge Querol, Symeon Chatzinotas
Venue: International Conference on Communications (2026)
Research Areas: 6G-NTN, GNSS & Positioning, AI & Neuromorphic SatCom
DOI: 10.1109/icc59461.2026.11587695

Lightweight Deep Learning-Aided LDPC Decoding for 5G NR UAV Communications

Mon, 18 May 2026 00:00:00 +0000

Abstract & Overview

This research contribution by Carla E. García, Jorge Querol, Mario R. Camana, Symeon Chatzinotas (2026), published in IEEE Transactions on Aerospace and Electronic Systems, investigates “Lightweight Deep Learning-Aided LDPC Decoding for 5G NR UAV Communications” within the domains of 6G-NTN, AI & Neuromorphic SatCom. The work is part of Dr. Jorge Querol’s research portfolio in advanced satellite communications, non-terrestrial networks (NTN), and radio-frequency signal processing at SnT (University of Luxembourg) and UPC-BarcelonaTech.

Publication Metadata

Authors: Carla E. García, Jorge Querol, Mario R. Camana, Symeon Chatzinotas
Venue: IEEE Transactions on Aerospace and Electronic Systems (2026)
Research Areas: 6G-NTN, AI & Neuromorphic SatCom
DOI: 10.1109/infocom59046.2026.11571367

Performance analysis of the Cassegrain telescope on the QKD with Mathieu-Gauss Beams

Mon, 11 May 2026 00:00:00 +0000

Abstract & Overview

Mathieu-Gauss beams (MGBs), a distinctive class of structured light generated by modulating the angular and radial components of Gaussian beams with Mathieu functions, exhibit propagation characteristics that make them promising candidates for free-space optical (FSO) and quantum communication links. In this study, the scintillation behaviour of MGBs under weak atmospheric turbulence is analysed to derive the effective visibility and to quantify its impact on the quantum bit error rate (QBER) and secret key rate (SKR) in quantum key distribution (QKD) systems employing Cassegrain-type transmitters. Numerical simulations are performed using a random phase screen method based on the modified von Kármán spectrum for even and odd MGB modes under various telescope configurations. QBER is modelled as a function of effective visibility derived from the scintillation index. The results demonstrate that the use of a Cassegrain telescope significantly suppresses scintillation-induced degradation, reduces QBER, and enhances SKR, with improvements of up to 80% compared to free-space propagation without telescopic correction. However, the performance enhancement is strongly mode-dependent, with certain MGB orders exhibiting greater turbulence resilience. These findings highlight the importance of transmitter geometry and beam-structure optimisation in improving the robustness and efficiency of structured-light-based FSO-QKD systems.

Publication Metadata

Authors: S. Oktay, Mert Bayraktar, Francesco Vista, Jorge Querol, Yves Schmit, S. Chatzinotas
Venue: Scientific Reports (2026)
Research Areas: AI & Neuromorphic SatCom, Beamforming & MIMO, Quantum & Optical Space Links
DOI: 10.1038/s41598-026-51915-y
Open Access Repository: ORBiLu – University of Luxembourg

Hybrid Deep Learning Decoder for Satellite Communication Systems

Mon, 13 Apr 2026 00:00:00 +0000

Abstract & Overview

This research contribution by Carla E. García, Mario R. Camana, Marcele O. K. Mendonça, Jorge Querol et al. (2026), published in IEEE Wireless Communications and Networking Conference Workshops (WCNCW), investigates “Hybrid Deep Learning Decoder for Satellite Communication Systems” within the domains of Satellite Communications, AI & Neuromorphic SatCom. The work is part of Dr. Jorge Querol’s research portfolio in advanced satellite communications, non-terrestrial networks (NTN), and radio-frequency signal processing at SnT (University of Luxembourg) and UPC-BarcelonaTech.

Publication Metadata

Authors: Carla E. García, Mario R. Camana, Marcele O. K. Mendonça, Jorge Querol, Symeon Chatzinotas
Venue: IEEE Wireless Communications and Networking Conference Workshops (WCNCW) (2026)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/wcncw67598.2026.11555163

Effect of the Cassegrain Telescope on the scintillation of Mathieu-Gauss beams

Thu, 18 Sep 2025 00:00:00 +0000

Abstract & Overview

The scintillation index plays a crucial role in the performance of free space optics (FSO) and quantum key distribution (QKD) systems. Enhancement in the scintillation index causes an increase in the bit error rate and a decrease in the key rate. In this paper, we studied the effect of the Cassegrain telescope on the scintillation of Mathieu-Gauss beams (MGB) in a weak turbulent atmosphere. We model the atmosphere by using the random phase screen numerical approach. We benefit from the hard aperture function when modeling the telescope. We compare the point-like scintillation values with and without the Cassegrain telescope. We research even and odd modes of the MGB. We observe that the scintillation index decreases drastically when using the Cassegrain telescope. In addition, we investigate that the scintillation index decreases when the expansion order rises. Similarly, we see that there is an inverse relation between the first complex expansion coefficient at a short distance. An increase in the second complex expansion coefficient shows its advantage at longer distances by mitigating scintillation. We anticipate that our results will be useful for the optical engineers to design FSO and QKD systems.

Publication Metadata

Authors: Mert Bayraktar, Francesco Vista, Jorge Querol, Yves Schmit, Symeon Chatzinotas
Venue: IEEE International Conference on Space Optical Systems and Applications (ICSOS) (2025)
Research Areas: AI & Neuromorphic SatCom, Beamforming & MIMO, Quantum & Optical Space Links
DOI: 10.1117/12.3063944
Open Access Repository: ORBiLu – University of Luxembourg

A Machine Learning-Based Receiver for Mitigating Nonlinear Distortion in OFDM Systems for 5G

Mon, 07 Jul 2025 00:00:00 +0000

Abstract & Overview

This work introduces a convolutional neural network (CNN)-based receiver designed for channel estimation, equalization, and symbol demapping in orthogonal frequency-division multiplexing (OFDM) systems. The proposed receiver is specifically developed to mitigate nonlinear distortions, particularly under low input back-off (IBO), thereby markedly enhancing signal quality and energy efficiency. By significantly reducing the bit error rate (BER) and outperforming traditional methods, the CNN-based receiver establishes itself as a highly robust solution for next-generation communication technologies. These advancements are pivotal for the development of reliable and efficient communication networks, particularly in the context of the fifth generation (5G) and beyond. Furthermore, this work contributes to the integration of terrestrial and non-terrestrial networks by addressing critical challenges in mitigating nonlinear distortions in satellite and hybrid communication systems using AI-driven techniques.

Publication Metadata

Authors: Marcele O. K. Mendonça, Francisco J. Martín Vega, Geoffrey Eappen, Carla E. García, Abuzar B. M. Adam, Jorge Querol, Beatriz Soret, Symeon Chatzinotas
Venue: IEEE International Mediterranean Conference on Communications and Networking (MeditCom) (2025)
Research Areas: 6G-NTN, AI & Neuromorphic SatCom
DOI: 10.1109/meditcom64437.2025.11104481
Open Access Repository: ORBiLu – University of Luxembourg

Machine Learning-Driven Framework for Reducing PAPR in Satellite Communication Systems

Tue, 17 Jun 2025 00:00:00 +0000

Abstract & Overview

High peak-to-average power ratio (PAPR) in orthogonal frequency division multiplexing (OFDM) signals presents a persistent challenge in satellite communications (SatCom), impacting signal quality and causing adjacent channel interference. This paper introduces a novel framework that combines the elastic net-based machine learning (ML) model with the partial transmit sequence (PTS) technique to effectively reduce PAPR. Additionally, the potential of artificial intelligence (AI) approaches are investigated, specifically swarm intelligence and ML methods, for high-performance, low-complexity solutions. In this regard, ML models are applied to mitigate PAPR in SatCom networks under the presence of a traveling wave tube amplifier (TWTA) model and a land mobile satellite (LMS) channel, employing 16-quadrature amplitude modulation (16-QAM). Compared with the baseline schemes, simulation results demonstrate that the proposed ML framework, integrating principal component analysis (PCA) with the elastic net learning model, achieves comparable PAPR performance and minimal computational complexity.

Publication Metadata

Authors: Carla E. García, Francisco J. Martin Vega, Mario R. Camana, Jorge Querol, Saud Althunibat, Khalid A. Qaraqe, Symeon Chatzinotas
Venue: IEEE Vehicular Technology Conference (2025)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/vtc2025-spring65109.2025.11174301
Open Access Repository: ORBiLu – University of Luxembourg

Resource Allocation Under Uncertainty in LEO Satellite Constellation Networks

Mon, 24 Mar 2025 00:00:00 +0000

Abstract & Overview

Low Earth Orbit (LEO) satellite constellations consist of numerous satellites orbiting at different altitudes to serve diverse terrestrial users. Efficient resource management in such dynamic and large-scale networks presents a significant challenge. This paper studies Resource Blocks (RBs) and transmit power allocation at each LEO satellite, aiming at enhancing network performance while meeting Quality of Service (QoS) requirements. A stochastic optimization problem is formulated where the required QoS by each user is expressed as a chance constraint of the minimum data rate requirements considering network dynamics and uncertainties in channel conditions and traffic demands. The Conditional Value at Risk (CVaR) is employed to reformulate the chance constraint into a convex form and achieve a robust solution. Then, an alternating optimization approach is applied to solve the optimization problem. Through simulations using real data from the Starlink constellation, we demonstrate the efficacy of the proposed approach in improving network data rates while maintaining the required QoS levels.

Publication Metadata

Authors: Madyan Alsenwi, Eva Lagunas, Jorge Querol, Yan Kyaw Tun, Symeon Chatzinotas
Venue: IEEE Wireless Communications and Networking Conference (2025)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/wcnc61545.2025.10978342

Enhanced demodulator for 5G NTN using spatio-temporal attention convolutional autoencoder and Akida Brainchip SNN

Sat, 01 Feb 2025 00:00:00 +0000

Abstract & Overview

This paper presents a novel approach to overcoming challenges in 5G and 6G mobile satellite systems (MSS) in Low Earth Orbit (LEO), focusing on Non-Line-of-Sight (NLOS) issues in 5G Non-Terrestrial Networks (NTN) that connect directly with handheld devices. We utilize a Convolutional Neural Network (CNN) with a Spatio-Temporal Attention Network (STAN) autoencoder, which is then converted into a Spiking Neural Network (SNN) using Brainchip Akida’s Meta TF Software Framework. This integration of neuromorphic processing aims to enhance energy efficiency, reduce computational demands, and increase data transmission rates, optimizing Channel State Information (CSI) in compliance with 3GPP standards. Our STAN-CNN-SNN architecture achieves a 85% reduction in computational requirements, leading to decrease in power consumption, and increase in data rates within the C-Band spectrum. Simulations with LEO satellite MSS parameters demonstrate significant advancements in communication systems. The numerical results demonstrates substantial computational reductions with minimal capacity trade-offs.

Publication Metadata

Authors: Swetha Varadarajulu, Marcele O. K. Mendonça, Geoffrey Eappen, Jorge Querol, Symeon Chatzinotas
Venue: IET conference proceedings. (2025)
Research Areas: 6G-NTN, AI & Neuromorphic SatCom
DOI: 10.1049/icp.2024.4619
Open Access Repository: ORBiLu – University of Luxembourg

5G-NR Over Transparent Payload GEO Satellites: A Hands-On Approach Using OpenAirInterface5G-NTN

Wed, 01 Jan 2025 00:00:00 +0000

Abstract & Overview

The inclusion of Non-Terrestrial Network (NTN) components has significantly enhanced the reach of 5G networks. OpenAirInterface5G (OAI) has developed an open-source, Software-Defined Radio (SDR)-based framework for 5G-NTN, using its Terrestrial Network (TN) protocol stack as the baseline. OAI’s 5G-NTN adaptations are still evolving, requiring in-lab validations and field trials to assess its effectiveness in addressing the unique challenges of NTN components and channel characteristics. Live satellite tests, unlike simulations, demand manual tuning of key parameters like carrier frequency offset, timing offsets, and gain calibration. In this work, we present a practical approach for deploying 5G over GEO satellites using the OAI 5G-NTN suite, addressing (a) satellite channel impairments and (b) limitations in OAI’s current 5G-NTN implementation. Our work provides step-by-step calibrations, ensuring both experiment reproducibility and the realization of a full 5G-NTN link. We further identify the performance bottlenecks and experiment with (a) Radio Link Control Acknowledgment Mode (RLC-AM) parameters and (b) Low-Density Parity Check (LDPC) iterations to improve end-to-end throughput. We validate our methods via live tests over a transparent payload GEO satellite. We believe that our work represents a critical step in bridging the gap between lab-based 5G-NTN emulation and live satellite testing, offering valuable insights to advance 5G-NTN research and development.

Publication Metadata

Authors: Sumit Kumar, Jevgenij Krivochiza, Türker Yilmaz, Jorge Querol, Symeon Chatzinotas, Stefano Andrenacci, Joël Grotz
Venue: IEEE Open Journal of the Communications Society (2025)
Research Areas: 6G-NTN, Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/ojcoms.2025.3586871
Open Access Repository: ORBiLu – University of Luxembourg

Joint Holographic Beamforming and User Scheduling With Individual QoS Constraints

Wed, 01 Jan 2025 00:00:00 +0000

Abstract & Overview

Reconfigurable holographic surfaces (RHS) have emerged as a transformative material technology, enabling dynamic control of electromagnetic waves to generate versatile holographic beam patterns. This paper addresses the problem of joint hybrid holographic beamforming and user scheduling under per-user minimum quality-of-service (QoS) constraints, a critical challenge in resource-constrained networks. However, such a problem results in mixed- integer non-convex optimization, making it difficult to identify feasible solutions efficiently. To overcome this challenge, we propose a novel iterative optimization framework that jointly solves the problem to maximize the RHS-assisted network sum-rate, efficiently managing holographic beamforming patterns, dynamically scheduling users, and ensuring the minimum QoS requirements for each scheduled user. The proposed framework relies on zero-forcing digital beamforming, gradient-ascent-based holographic beamformer optimization, and a greedy user selection principle. Our extensive simulation results validate the effectiveness of the proposed scheme, demonstrating their superior performance compared to the benchmark algorithms in terms of sum-rate performance, while meeting the minimum per-user QoS constraints.

Publication Metadata

Authors: Chandan Kumar Sheemar, Christo Kurisummoottil Thomas, George C. Alexandropoulos, Jorge Querol, Symeon Chatzinotas, Walid Saad
Venue: IEEE Transactions on Vehicular Technology (2025)
Research Areas: AI & Neuromorphic SatCom, Beamforming & MIMO
DOI: 10.1109/tvt.2025.3569401

5G Non-Terrestrial Networks with OpenAirInterface: An Experimental Study over GEO Satellites

Mon, 01 Jan 2024 00:00:00 +0000

Abstract & Overview

The 3rd Generation Partnership Project (3GPP) aims to integrate non-terrestrial networks (NTNs) with terrestrial 5G networks. In this context, prototyping and testing are essential to demonstrate the readiness of new 5G-NTN releases. However, commercial 5G protocol stack implementations are usually costly and closed solutions, which makes it challenging for universities and nonprofit research institutions to adapt and customize them for 5G-NTN testing and development purposes. Software-defined radio testbeds that utilize open-source software implementations are an attractive alternative. In this article, we describe our protocol stack adaptation of an open-source implementation for 5G-NTN based on OpenAirInterface (OAI), which runs on commodity hardware. We evaluate the performance of our 5G-NTN in various layers in real-world environments with a transparent geostationary satellite. We validate our testbed with a variety of Internet applications. These include streaming video, web browsing, and voice over IP. The results indicate that the current implementation utilizing the 5 MHz bandwidth is reliable over several hours and achieves both downlink and uplink speeds of 3.6 Mb/s while maintaining a typical geostationary latency of approximately 530 ms. The tests demonstrate that our 5G-NTN testbed is an reliable alternative to costly commercial implementations.

Publication Metadata

Authors: Florian Völk, Thomas Schlichter, Sumit Kumar, Robert T. Schwarz, Andreas Knopp, Marwan Hammouda, Thomas Heyn, Jorge Querol, Symeon Chatzinotas, Adam Kapovits
Venue: IEEE Access (2024)
Research Areas: 6G-NTN, Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/access.2024.3483958
Open Access Repository: ORBiLu – University of Luxembourg

Flexible Payload Configuration for Satellites using Machine Learning

Mon, 01 Jan 2024 00:00:00 +0000

Abstract & Overview

Satellite communications, essential for modern connectivity, extend access to maritime, aeronautical, and remote areas where terrestrial networks are unfeasible. Current GEO systems distribute power and bandwidth uniformly across beams using multi-beam footprints with fractional frequency reuse. However, recent research reveals the limitations of this approach in heterogeneous traffic scenarios, leading to inefficiencies. To address this, this paper presents a machine learning (ML)-based approach to Radio Resource Management (RRM).We treat the RRM task as a regression ML problem, integrating RRM objectives and constraints into the loss function that the ML algorithm aims at minimizing. Moreover, we introduce a context-aware ML metric that evaluates the ML model’s performance but also considers the impact of its resource allocation decisions on the overall performance of the communication system.

Publication Metadata

Authors: Marcele OK Mendonça, Flor G Ortiz-Gomez, Jorge Querol, Eva Lagunas, Juan A Vásquez Peralvo, Victor Monzon Baeza, Symeon Chatzinotas, Bjorn Ottersten
Venue: 2024 IEEE International Conference on Machine Learning for Communication (2024)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/icmlcn59089.2024.10624839
Open Access Repository: ORBiLu – University of Luxembourg

Graph Neural Network Pooling for BCH Channel Decoding in Software Defined Satellites

Mon, 01 Jan 2024 00:00:00 +0000

Abstract & Overview

This paper delves into the transformative impact of Deep Learning (DL) techniques on decoding tasks at the physical layer onboard regenerative software-defined satellites, reshaping traditional error correction methodologies. Specifically, we focus on the integration of Graph Neural Networks (GNNs) for channel decoding, which offers a fresh perspective by adeptly handling graph-structured data and effectively modelling intricate interference and channel dependencies. The study systematically explores the potential performance tradeoffs that arise from modifying the graph structure. Furthermore, we extend our investigation by implementing the message-passing algorithm with GNN, employing a topk pooling method following pick, prune, and link optimization strategies. This strategic approach aims to mitigate computational complexity and minimize latency, by 30 to 35 % which is particularly advantageous for decoding BCH codes. This advancement promises to enhance the efficiency of communication systems sianificantly,

Publication Metadata

Authors: Swetha Varadarajulu, Victor Monzon Baeza, Jorge Querol, Marcele OK Mendonca, Symeon Chatzinotas
Venue: 2024 IEEE International Conference on Communications Workshops (ICC (2024)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/iccworkshops59551.2024.10615375

Performance Evaluation of Neuromorphic Hardware for Onboard Satellite Communication Applications

Mon, 01 Jan 2024 00:00:00 +0000

Abstract & Overview

Spiking neural networks (SNNs) implemented on neuromorphic processors (NPs) can enhance the energy efficiency of deployments of artificial intelligence (AI) for specific workloads. As such, NPs represent an interesting opportunity for implementing AI tasks power-limited onboard satellite communication spacecraft. In this article, we disseminate the findings of a recently completed study which targeted the comparison, in terms of performance and power-consumption, of different satellite communication use cases implemented on standard AI accelerators and on NPs. In particular, the article describes three prominent use cases, namely payload resource optimization, onboard interference detection and classification, and dynamic receive beamforming; and compares the performance of conventional convolutional neural networks (CNNs) implemented on Xilinx’s VCK5000 Versal development card, and SNNs on Intel’s neuromorphic chip Loihi 2.

Publication Metadata

Authors: Eva Lagunas, Flor Ortiz, Geoffrey Eappen, Saed Daoud, Wallace Alves Martins, Jorge Querol, Symeon Chatzinotas, Nicolas Skatchkovsky, Bipin Rajendran, Osvaldo Simeone
Venue: arXiv preprint arXiv:2401.06911 (2024)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/mwc.016.2300560
Open Access Repository: ORBiLu – University of Luxembourg

5G NTN LEO based demonstrator using OpenAirInterface5G

Sun, 01 Jan 2023 00:00:00 +0000

Abstract & Overview

3GPP Release-17 formally recognizes Non- Terrestrial Network (NTN) components as an integral part of future telecommunication networks. The integration of 5G with NTN has gained significant traction due to the joint effort from academia, industry, and government space agencies. The first phase of 5G-NTN prototype development has been successful using GEO satellites. Moving ahead, LEO satellites can provide higher data rates and lower latency compared to GEO. In this paper, we discuss the 3GPP Release-17 compliant cross-layered adaptations done in OpenAirInterface5G during the project 5G-LEO (OpenAirInterface5G Extension for 5G Satellite Links). 5G-LEO aims to provide direct access to 5G services to a ground UE via a transparent payload LEO satellite. To the best of our knowledge, 5G-LEO is the first work involving the adaptation of 5G protocol addressing the challenges presented by the LEO satellite channel for example high and time-varying Doppler, Round-Trip-Time; and frequent handover. A Software Defined Radio-based end-to-end demonstrator has been developed during the project. Results from the experiments conducted during functional validation over the demonstrator are presented in this work. Our initial experiments show promising results and the feasibility of direct access to 5G services through transparent payload LEO satellites.

Publication Metadata

Authors: Sumit Kumar, Chandan Kumar Sheemar, Jorge Querol, Turker Yilmaz, Symeon Chatzinotas, Marwan Hammouda, Thomas Heyn, Thomas Schlichter, Paulo Marques, Luis Pereira
Venue: ICSSC (2023)
Research Areas: 6G-NTN, Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1049/icp.2024.0822
Open Access Repository: ORBiLu – University of Luxembourg

Experimental Study of the Effects of RLC Modes for 5G-NTN applications using OpenAirInterface5G

Sun, 01 Jan 2023 00:00:00 +0000

Abstract & Overview

Provisioning of 5G services via Non-Terrestrial Networks (5G-NTN) has become a reality. Currently, 5G-NTN is being developed by adapting the 5G Terrestrial Network (5G-TN) protocol which presents several challenges as the satellite channel is significantly different from terrestrial channels. The retransmission mechanism is one of them. Recent works on 5G-NTN have followed the approach of disabling retransmissions from the 5G protocol stack such as Hybrid Automatic Repeat Request (HARQ) at the MAC layer and Automatic Repeat Request (ARQ) at the RLC layer while delegating it to the application layer. This approach degrades the end-user-throughput and latency. In this work, we experimentally study the effect of enabling ARQ retransmission, by using RLC Acknowledged Mode (RLC-AM) in a GEO-based 5G-NTN which is susceptible to packet loss caused by low SNR. We conduct realtime experiments to compare the effects of RLC-AM and RLC Unacknowledged Mode(RLC-Um)on applications(VoIP, video stream, file transfer) using TCP and UDP for different SNR regimes. We have used OpenAirInterface5G-NTN, which is developed to perform realtime 5G-NTN experiments, and a satellite channel emulator. We observe that for low SNR, RLC-AM performs better than RLC-UM in achieving the required bitrate and packet error rate. The reason being RLC-AM recovers the lost packets earlier in the protocol stack without delegating the retransmissions to the application layer. This becomes especially useful when HARQ is disabled. We believe that our experimental study will complement the ongoing theoretical research and help improve the procedures of the Radio Resource Control(RRC) layer in 5G-NTN-specific applications.

Publication Metadata

Authors: Sumit Kumar, Chandan Kumar Sheemar, Jorge Querol, Amirhossein Nik, Symeon Chatzinotas
Venue: 2023 IEEE Globecom Workshops (GC Wkshps) (2023)
Research Areas: 6G-NTN, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/gcwkshps58843.2023.10464560
Open Access Repository: ORBiLu – University of Luxembourg

Flexible Payload Configuration for Satellites using Machine Learning

Sun, 01 Jan 2023 00:00:00 +0000

Abstract & Overview

Publication Metadata

Authors: Marcele OLIVEIRA KUHFUSS DE MENDONÇA, Flor de Guadalupe ORTIZ GOMEZ, Jorge Querol, Eva Lagunas, Juan Andres VASQUEZ-PERALVO, Victor MONZON BAEZA, Symeon Chatzinotas, Björn OTTERSTEN
Venue: IEEE International Conference on Machine Learning for Communication (2023)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.1109/icmlcn59089.2024.10624839
Open Access Repository: ORBiLu – University of Luxembourg

Onboard processing in satellite communications using ai accelerators

Sun, 01 Jan 2023 00:00:00 +0000

Abstract & Overview

Satellite communication (SatCom) systems operations centers currently require high human intervention, which leads to increased operational expenditure (OPEX) and implicit latency in human action that causes degradation in the quality of service (QoS). Consequently, new SatCom systems leverage artificial intelligence and machine learning (AI/ML) to provide higher levels of autonomy and control. Onboard processing for advanced AI/ML algorithms, especially deep learning algorithms, requires an improvement of several magnitudes in computing power compared to what is available with legacy, radiation-tolerant, space-grade processors in space vehicles today. The next generation of onboard AI/ML space processors will likely include a diverse landscape of heterogeneous systems. This manuscript identifies the key requirements for onboard AI/ML processing, defines a reference architecture, evaluates different use case scenarios, and assesses the hardware landscape for current and next-generation space AI processors.

Publication Metadata

Authors: Flor Ortíz, Víctor Monzón Baeza, Luis Manuel Garcés-Socarrás, Juan A. Vásquez-Peralvo, Jorge Luis González Ríos, Gianluca Fontanesi, Eva Lagunas, Jorge Querol, Symeon Chatzinotas
Venue: Aerospace (2023)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom
DOI: 10.3390/aerospace10020101
Open Access Repository: ORBiLu – University of Luxembourg

Robust Beamforming for IRS Aided MIMO Full Duplex Systems

Sun, 01 Jan 2023 00:00:00 +0000

Abstract & Overview

In this paper, a novel robust beamforming for an intelligent reflecting surface (IRS) assisted FD system is presented. Since perfect channel state information (CSI) is often challenging to acquire in practice, we consider the case of imperfect CSI and adopt a statistically robust beamforming approach to maximize the ergodic weighted sum rate (WSR). We also analyze the achievable WSR of an IRS-assisted FD with imperfect CSI, for which the lower and the upper bounds are derived. The ergodic WSR maximization problem is tackled based on the expected Weighted Minimum Mean Squared Error (WMMSE), which is guaranteed to converge to a local optimum. The effectiveness of the proposed design is investigated with extensive simulation results. It is shown that our robust design achieves significant performance gain compared to the naive beamforming approaches and considerably outperforms the robust Half-Duplex (HD) system.

Publication Metadata

Authors: Chandan Kumar Sheemar, Jorge Querol, Sourabh Solanki, Sumit Kumar, Symeon Chatzinotas
Venue: GLOBECOM 2023-2023 IEEE Global Communications Conference (2023)
Research Areas: AI & Neuromorphic SatCom, Beamforming & MIMO
DOI: 10.48550/arxiv.2308.08016

5G-NTN GEO-based in-lab demonstrator using OpenAirInterface5G

Sat, 01 Jan 2022 00:00:00 +0000

Abstract & Overview

This research contribution by Sumit Kumar, Abdelrahman Abdalla, Oltjon Kodheli, Jorge Querol et al. (2022), published in 11th Advanced Satellite Multimedia Conference, investigates “5G-NTN GEO-based in-lab demonstrator using OpenAirInterface5G” within the domains of 6G-NTN, Satellite Communications, AI & Neuromorphic SatCom. The work is part of Dr. Jorge Querol’s research portfolio in advanced satellite communications, non-terrestrial networks (NTN), and radio-frequency signal processing at SnT (University of Luxembourg) and UPC-BarcelonaTech.

Publication Metadata

Authors: Sumit Kumar, Abdelrahman Abdalla, Oltjon Kodheli, Jorge Querol, Symeon Chatzinotas, Thomas Schlichter, Guido Casati, Thomas Heyn, Florian Volk, Sertac Kaya
Venue: 11th Advanced Satellite Multimedia Conference (2022)
Research Areas: 6G-NTN, Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds

Differential phase compensation in over-the-air precoding test-bed for a multi-beam satellite

Sat, 01 Jan 2022 00:00:00 +0000

Abstract & Overview

This article presents a closed-loop differential phase compensation system for a precoding-enabled multibeam satellite forward link and its validation by live experiments on a GEO satellite scenario. The precoding operation avoids inter-beam interference and maximizes the spectrum efficiency by full frequency reuse as an alternative to the traditional two-color or four-color reuse methods proposed in the DVB-S2 standard. However, the satellite payload introduces differential phase and frequency impairments, which can degrade the precoding performance. This work describes the implementation of the differential phase and frequency tracking and compensation loop in an end-to-end testbed over a multibeam satellite system with independent local oscillators. The developed system performs end-to-end real-time communication over the satellite link, including channel measurements and precompensation. Results are validated by an over-the-air demonstration using two beams of the SES-14 multibeam satellite. Each beam is transmitted by independent transponders, which results in differential frequency and phase offsets due to the transponder undisciplined local oscillators. This phase offset makes it impossible to use precoding without the phase compensation loop. We prove that the implemented system can successfully track and compensate the differential phase and frequency to improve precoding performance.

Publication Metadata

Authors: Liz Martínez Marrero, Juan Carlos Merlano Duncán, Jorge Querol, Nicola Maturo, Jevgenij Krivochiza, Symeon Chatzinotas, Björn Ottersten
Venue: 2022 IEEE Wireless Communications and Networking Conference (WCNC) (2022)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom, Beamforming & MIMO
DOI: 10.1109/wcnc51071.2022.9771918
Open Access Repository: ORBiLu – University of Luxembourg

Machine learning for radio resource management in multibeam GEO satellite systems

Sat, 01 Jan 2022 00:00:00 +0000

Abstract & Overview

Satellite communications (SatComs) systems are facing a massive increase in traffic demand. However, this increase is not uniform across the service area due to the uneven distribution of users and changes in traffic demand diurnal. This problem is addressed by using flexible payload architectures, which allow payload resources to be flexibly allocated to meet the traffic demand of each beam. While optimization-based radio resource management (RRM) has shown significant performance gains, its intense computational complexity limits its practical implementation in real systems. In this paper, we discuss the architecture, implementation and applications of Machine Learning (ML) for resource management in multibeam GEO satellite systems. We mainly focus on two systems, one with power, bandwidth, and/or beamwidth flexibility, and the second with time flexibility, i.e., beam hopping. We analyze and compare different ML techniques that have been proposed for these architectures, emphasizing the use of Supervised Learning (SL) and Reinforcement Learning (RL). To this end, we define whether training should be conducted online or offline based on the characteristics and requirements of each proposed ML technique and discuss the most appropriate system architecture and the advantages and disadvantages of each approach.

Publication Metadata

Authors: Flor Ortíz, Lei Lei, Eva Lagunas, Ramón Martínez Rodríguez‐Osorio, Daniele Tarchi, Jorge Querol, Miguel A. Salas‐Natera, Symeon Chatzinotas
Venue: Electronics (2022)
Research Areas: Satellite Communications, AI & Neuromorphic SatCom, Beamforming & MIMO
DOI: 10.3390/electronics11070992
Open Access Repository: ORBiLu – University of Luxembourg

OpenAirInterface as a platform for 5G-NTN Research and Experimentation

Sat, 01 Jan 2022 00:00:00 +0000

Abstract & Overview

Technical advancements and experimental works for the integration of 5G and Non-Terrestrial Networks (NTN) have gained significant traction over the past few years. NTN components have been officially included in the 5G ecosystem by 3GPP in the latest Release-17. 5G-NTN research is ongoing and it is desirable to have a platform that facilitates quick prototyping of the proof-of-concept methods. OpenAirInterface(OAI) is an open-source experimental yet 3GPP standard-compliant Software Defined Radio (SDR) based protocol stack that has been widely known for implementing 4G/5G technologies. Due to its proven capabilities and flexibility, OAI is currently in the developmental process of integrating adaptations for the 5G-NTN. In this work, we discuss the peculiar features of OAI which are shaping it towards becoming a preferred tool for research and experimentation related to 5G-NTN. We provide details of completed/ongoing 5G-NTN projects leveraging OAI to achieve their objectives. In particular, we discuss 5G-GOA and 5G-LEO where critical adaptations in OAI are being done to support 5G-NTN use-cases. Such adaptations enable direct-access between UE and gNB via transparent payload Geostationary (5G-GOA) and Non-geostationary satellites (5G-LEO). Both projects have closely followed 3GPP discussions over 5G-NTN and the adaptations are compliant with the currently frozen 3GPP Release-17. OAI adaptations from both projects will be merged into the main development branch of OAI. We also provide a future roadmap of OAI towards 5G-NTN development. We believe that the pioneering steps taken in the course of the aforementioned projects will establish OAI as a preferred tool for 5G-NTN research and experimentations.

Publication Metadata

Authors: Sumit Kumar, Ashish Kumar Meshram, Abdelrahman Astro, Jorge Querol, Thomas Schlichter, Guido Casati, Thomas Heyn, Florian Völk, Robert T. Schwarz, Andreas Knopp, Paulo Marques, Luis Pereira, Roberto Magueta, Adam Kapovits, Florian Kaltenberger
Venue: 2022 IEEE Future Networks World Forum (FNWF) (2022)
Research Areas: 6G-NTN, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/fnwf55208.2022.00094
Open Access Repository: ORBiLu – University of Luxembourg

Radio-frequency interference location, detection and classification using deep neural networks

Wed, 01 Jan 2020 00:00:00 +0000

Abstract & Overview

Global Navigation Satellite System (GNSS) signals are used in Earth Observation for Radio Occultation and Reflectometry. The increasing effects of Radio-Frequency Interferences (RFI) on the performance of these receivers and navigation have suddenly sparked serious concerns due to their proliferation. Detection and mitigation of RFI heavily relies on the nature and location of the interfering sources. In some cases, null-steering or shielding can be used to mitigate RFI effects. In this work, a system to detect and locate RFI sources is presented, including signal classification and recording for countermeasure-related decision-making.

Publication Metadata

Authors: A. Perez, Jorge Querol, H. Park, A. Camps
Venue: IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium (2020)
Research Areas: RFI Mitigation & GNSS Security, AI & Neuromorphic SatCom
DOI: 10.1109/igarss39084.2020.9324532

3CAT-3/MOTS, an experimental nanosatellite for multispectral and GNSS-R earth observation: airborne optical and GNSS-R campaign

Mon, 01 Jan 2018 00:00:00 +0000

Abstract & Overview

The3Cat-3/MOTS mission is a joint initiative between the Institut Cartogràfic i Geològic de Catalunya (ICGC) and the Universitat Politècnica de Catalunya-BarcelonaTech (UPC) to foster new and innovative technologies on Earth Observation (EO) based on the data fusion of Global Navigation Satellite Systems Reflectometry (GNSS-R) and optical payloads on a 6U CubeSat platform. The final objective of the mission is to provide soil moisture mapping through the GNSS-R payload and improve its resolution by data fusion with the multi-spectral optical data acquired. This technique has been successfully applied to SMOS, but never performed from a 6U CubeSat carrying both payloads. An airborne optical and GNSS-R field experiment has been carried out to test/develop the algorithm and to analyze the results both separately (GNSS-R + optical data) and as a soil moisture product, once performed the data fusion.

Publication Metadata

Authors: Jordi Castellvi-Esturi, Adriano Camps, Jordi Corbera, Raul Onrubia, Ramon Alamús, Daniel Pascual, Jorge Querol, Hyuk Park
Venue: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (2018)
Research Areas: Satellite Communications, JCAS & Earth Observation, GNSS & Positioning, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
DOI: 10.1109/igarss.2018.8518216

Determination of sea correlation time at L-Band with airborne reflected new GNSS signals

Mon, 01 Jan 2018 00:00:00 +0000

Abstract & Overview

The maximum coherent integration time of GNSS reflected (GNSS-R) signals over sea depends on the sea state, as well as on the geometry formed by the receiver, the GNSS satellite and the reflection point. In this paper, real data obtained with a dedicated airborne instrument named MALYGNSS (Multi-band Airborne L-Band reflectometrY with GNSS) is used to acquire GPS L1 C/A and L2C, and Galileo E1OS signals. The direct signals are used as a reference to detect any phase shift due to data bits changes and the presence of a residual Doppler frequency. These phase transitions are removed in the reflected signals, and coherent correlations of different lengths are performed in order to study sea correlation time.

Publication Metadata

Authors: D. Pascual, R. Onrubia, Jorge Querol, J. Castellvi-Esturi, H. Park, A. Camps
Venue: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (2018)
Research Areas: GNSS & Positioning, AI & Neuromorphic SatCom
DOI: 10.1109/igarss.2018.8518552

RFI analysis and mitigation in airborne GNSS-R campaign

Mon, 01 Jan 2018 00:00:00 +0000

Abstract & Overview

Radio-Frequency Interference (RFI) is one of the most concerning topics in Global Navigation Satellite Systems (GNSS) and GNSS - Reflectometry (GNSS-R) because any undesired signal present at the antenna can corrupt the received signal and the eventual geophysical measurements. The purpose of this paper is two-fold. First, an RFI analysis is performed to the raw data obtained from an airborne dual-band GNSS reflectometer. Finally, the Front-End GNSS Interference eXcisor (FENIX) mitigation algorithm is applied to the raw data, and then the Signal-to-Noise Ratio (SNR) improvement at the Delay-Doppler Map (DDM) is obtained. From the analysis of one of the datasets, two RFI signals were detected and characterized. Moreover, FENIX output signal was revealed to be much cleaner than before. The mean SNR improvement with coherent DDMs of 1 ms is 0.72 dB, whereas the SNR improvement increases to 1.49 dB when considering 50 incoherent averages. This improvement represents a reduction in the geophysical parameter estimation uncertainty.

Publication Metadata

Authors: Jorge Querol, R. Onrubia, D. Pascual, J. Castellvi-Esturi, H. Park, A. Camps
Venue: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (2018)
Research Areas: JCAS & Earth Observation, RFI Mitigation & GNSS Security, GNSS & Positioning, AI & Neuromorphic SatCom
DOI: 10.1109/igarss.2018.8518827

First Delay Doppler Maps obtained with the Microwave Inteferometric Reflectometer (MIR)

Fri, 01 Jan 2016 00:00:00 +0000

Abstract & Overview

This work presents the first Delay Doppler Maps (DDMs) obtained with the Microwave Interferometric Reflectometer (MIR) airborne instrument. MIR is a GNSS Reflectometer (GNSS-R) which uses the conventional (cGNSS-R) and interferometric (iGNSS-R) techniques for ocean and land observation. It computes real-time sample-to-sample complex DDMs with averaging and alignment, of up to 4 simultaneous GPS/Galileo satellites at the L1/E1, and L5/E5a bands. Satellites are tracked with high directivity antennas with beam steering. The MIR instrument is designed to validate and compare both GNSS-R techniques with the new available signals, with special focus in the GEROS-ISS payload, and to contribute to the development of geophysical retrieval algorithms.

Publication Metadata

Authors: D. Pascual, R. Onrubia, Jorge Querol, A. Alonso-Arroyo, H. Park, A. Camps
Venue: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (2016)
Research Areas: GNSS & Positioning, AI & Neuromorphic SatCom
DOI: 10.1109/igarss.2016.7729514

Disseny i implementació d’un servidor de pàgines web per a la supervisió i difusió de mesures a temps real d’una instal• lació fotovoltaica especı́fica per a la mesura en mòduls fotovoltaics

Sat, 01 Jan 2011 00:00:00 +0000

Abstract & Overview

This research contribution by Jorge Querol (2011), published in international conference proceedings, investigates “Disseny i implementació d’un servidor de pàgines web per a la supervisió i difusió de mesures a temps real d’una instal• lació fotovoltaica especı́fica per a la mesura en mòduls fotovoltaics” within the domains of AI & Neuromorphic SatCom. The work is part of Dr. Jorge Querol’s research portfolio in advanced satellite communications, non-terrestrial networks (NTN), and radio-frequency signal processing at SnT (University of Luxembourg) and UPC-BarcelonaTech.

Publication Metadata

Authors: Jorge Querol
Venue: Conference Paper (2011)
Research Areas: AI & Neuromorphic SatCom