Check our Zenodo community at TRANTOR Zenodo.
From 5G to 6G: Revolutionizing Satellite Networks through TRANTOR Foundation
Pol Henarejos, Xavier Artiga, Miguel Á. Vázquez, Màrius Caus, Musbah Shaat, Joan Bas, Lluís Blanco, & Ana I. Pérez-Neira
5G technology will drastically change the way satellite internet providers deliver services by offering higher data speeds, massive network capacity, reduced latency, improved reliability and increased availability. A standardised 5G ecosystem will enable adapting 5G to satellite needs. The EU-funded TRANTOR project will seek to develop novel and secure satellite network management solutions that allow scaling up heterogeneous satellite traffic demands and capacities in a cost-effective and highly dynamic way. Researchers also target the development of flexible 6G non-terrestrial access architectures. The focus will be on the design of a multi-orbit and multi-band antenna for satellite user equipment (UE), as well as the development of gNodeB (gNB) and UE 5G non-terrestrial network equipment to support multi-connectivity.
CVaR-based Robust Beamforming Framework for Massive MIMO LEO Satellite Communications
Madyan Alsenwi, Eva Lagunas, Hayder Al-Hraishawi, & Symeon Chatzinotas
This paper proposes a robust beamforming algorithm for massive multiple-input multiple-output (MIMO) low earth-orbit (LEO) satellite communications under uncertain channel conditions. Specifically, a Conditional Value at Risk (CVaR)-based stochastic optimization problem is formulated to optimize the hybrid digital and analog precoding aiming at maximizing the network data rate while considering the required Quality-of-Service (QoS) by each ground user. In particular, the CVaR is used as a risk measure of the downlink data rate to capture the high dynamic and random channel variations of the satellite network, achieving the required QoS under the worst-case scenario. Utilizing the decomposition and relaxation optimization techniques, an alternating optimization algorithm is developed to solve the formulated problem. Simulation results demonstrate the efficacy of the proposed approach in achieving the QoS requirements under uncertain satellite channel conditions.
Gateway Station Geographical Planning for Emerging Non-Geostationary Satellites Constellations
Victor Monzon Baez, Flor Ortiz, Eva Lagunas, Tedros Salih Abdu, & Symeon Chatzinotas
Among the recent advances and innovations in satellite communications, Non-Geostationary Orbit (NGSO) satellite constellations are gaining popularity as a viable option for providing widespread broadband internet access and backhauling services. However, a more complex ground segment with multiple ground stations is necessary due to these satellites’ high speeds and low altitudes. The complete dimensioning of the ground segment, including gateway optimal placement and the number of ground access points, remains a relevant open challenge. In this article, we provide an overview of the key factors that shall be considered for NGSO gateway station geographical planning. Subsequently, we propose a ground segment dimensioning approach that combines several criteria, such as rain attenuation, elevation angle, visibility, geographical constraints, and user traffic demands. The operational concept is first discussed, followed by a methodology that combines all these constraints into a single map-grid to select the best position for each gateway. Furthermore, a case study is presented, which demonstrates the performance of the proposed methodology, for one example constellation. Finally, we highlight relevant open challenges and key research directions in this area.
Single- and Multi-Connectivity for Multi-Satellite 6G Communication Networks
Mohammed Al-Ansi, Jorge Querol, Eva Lagunas, & Symeon Chatzinotas
This study explores the connectivity strategies for downlink multi-satellites in 6G communication networks. We begin with concepts, technologies, and trade-offs of Single-Connectivity (SC) and Multi-Connectivity (MC). Within the realm of MC, we present three different scenarios, one of which serves as a case study with a particular emphasis on Dual Connectivity (DC). This DC is performed between Geostationary Earth Orbit (GEO) and Low Earth Orbit (LEO) satellites for public safety systems. To improve reliability, we consider packet duplication mechanisms in addition to multi-band satellite capabilities. This supports the LEO link, addresses its limited availability, and facilitates a smooth handover between LEO satellites. Using link-level simulation, outage probability is examined by comparing the SC and MC modes under normal and adverse weather conditions. The findings of this study pave the way for more research to enhance connectivity solutions for more reliable and efficient global communication networks by bringing to light the MC opportunities for multi-satellite systems.
Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach
Achilles Machumilane, Alberto Gotta, Pietro Cassará, Claudio Gennaro, & Giuseppe Amato
In Non-Terrestrial Networks (NTNs), where LEO satellites and User Equipment (UE) move relative to each other, Line-of-Sight (LOS) tracking,and adapting to channel state variations due to endpoint movements are a major challenge. Therefore, continuous LOS estimation and channel impairment compensation are crucial for a UE to access a satellite and maintain connectivity. In this paper, we propose a Actor-Critic (AC)-Reinforcement Learning (RL) framework for traffic scheduling in NTN scenarios where the channel state is non-stationary due to the variability of LOS, which depends on the current satellite elevation. We deploy the framework as an agent in a Multi-Path Routing (MPR) scheme where the UE can access more than one satellite simultaneously to improve link reliability and throughput. We study how the agent schedules traffic on multiple satellite links by adopting the AC version of RL. The agent continuously trains based on variations in satellite elevation angles, handoffs, and relative LOS probabilities. We compare the agent retraining time with the satellite visibility intervals to investigate the effectiveness of the agent’s learning rate. We carry out performance analysis considering the dense urban area of Chicago, where high-rise buildings significantly affect the LOS. The simulation result show how the learning agent selects the scheduling policy when it is connected to a pair of satellites. The results also show that the retraining time of the learning agent is up to 0.1 times the satellite visibility time at certain elevations, which guarantees efficient use of satellite visibility.
A Federated Channel Modeling System using Generative Neural Networks
Saira Bano, Pietro Cassarà, Nicola Tonellotto, & Alberto Gotta
The paper proposes a data-driven approach to air-to-ground channel estimation in a millimeter-wave wireless network on an unmanned aerial vehicle. Unlike traditional centralized learning methods that are specific to certain geographical areas and inappropriate for others, we propose a generalized model that uses Federated Learning (FL) for channel estimation and can predict the air-to-ground path loss between a low-altitude platform and a terrestrial terminal. To this end, our proposed FL-based Generative Adversarial Network (FL-GAN) is designed to function as a generative data model that can learn different types of data distributions and generate realistic patterns from the same distributions without requiring prior data analysis before the training phase. To evaluate the effectiveness of the proposed model, we evaluate its performance using Kullback-Leibler divergence (KL), and Wasserstein distance between the synthetic data distribution generated by the model and the actual data distribution. We also compare the proposed technique with other generative models, such as FL-Variational Autoencoder (FL-VAE) and stand-alone VAE and GAN models. The results of the study show that the synthetic data generated by FL-GAN has the highest similarity in distribution with the real data. This shows the effectiveness of the proposed approach in generating data-driven channel models that can be used in different regions.
Toward a Fully-Observable Markov Decision Process With Generative Models for Integrated 6G-Non-Terrestrial Networks
Achilles Machumilane, Pietro Cassará, & Alberto Gotta
The upcoming sixth generation (6G) mobile networks require integration between terrestrial mobile networks and non-terrestrial networks (NTN) such as satellites and high altitude platforms (HAPs) to ensure wide and ubiquitous coverage, high connection density, reliable communications and high data rates. The main challenge in this integration is the requirement for line-of-sight (LOS) communication between the user equipment (UE) and the satellite. In this paper, we propose a framework based on actor-critic reinforcement learning and generative models for LOS estimation and traffic scheduling on multiple links connecting a user equipment to multiple satellites in 6G-NTN integrated networks. The agent learns to estimate the LOS probabilities of the available channels and schedules traffic on appropriate links to minimise end-to-end losses with minimal bandwidth. The learning process is modelled as a partially observable Markov decision process (POMDP), since the agent can only observe the state of the channels it has just accessed. As a result, the learning agent requires a longer convergence time compared to the satellite visibility period at a given satellite elevation angle. To counteract this slow convergence, we use generative models to transform a POMDP into a fully observable Markov decision process (FOMDP). We use generative adversarial networks (GANs) and variational autoencoders (VAEs) to generate synthetic channel states of the channels that are not selected by the agent during the learning process, allowing the agent to have complete knowledge of all channels, including those that are not accessed, thus speeding up the learning process. The simulation results show that our framework enables the agent to converge in a short time and transmit with an optimal policy for most of the satellite visibility period, which significantly reduces end-to-end losses and saves bandwidth. We also show that it is possible to train generative models in real time without requiring prior knowledge of the channel models and without slowing down the learning process or affecting the accuracy of the models.
Open Datasets for Satellite Radio Resource Control
Shahid, H., Miguel Ángel Vázquez, Henarejos, P., Shaat, M., Nuria Candelaria Trujillo Quijada, & Enrique Marín
In Non-Terrestrial Networks (NTN), achieving effective radio resource allocation across multi-satellite system, encompassing efficient channel and bandwidth allocation, effective beam management, power control and interference mitigation, poses significant challenges due to the varying satellite links and highly dynamic nature of user traffic. This calls for the development of an intelligent decision-making controller using Artificial Intelligence (AI) to efficiently manage resources in this complex environment. In this context, open datasets can play a crucial role in driving new advancement and facilitating research. Recognizing the significance, this paper aims to contribute the satellite communication research community by providing various open datasets that incorporate realistic traffic flow enabling a variety of uses cases. The primary objective of sharing these datasets is to facilitate the development and benchmarking of advanced resource management solutions, thereby improving the overall satellite communication systems. Furthermore, an application example focused on beam placement optimization via terminal clustering is provided. This assists in optimizing beam allocation task, enabling adaptive beamforming to effectively meet spatiotemporally varying user traffic demands and optimize resource utilization.
Functional Split Evaluation in NTN for LEO Satellites
Rashid, K., Leo, F., & Alexander, H
Functional split over non-terrestrial networks (NTN) is one of the key-enabling technologies in the next 5G+ and 6G networks, which allows the implementation of virtualized radio access network (vRAN), and the recent open RAN (ORAN) in NTN. Functional split is based on splitting the RAN functionalities into a centralized unit (CU) and a distributed unit (DU), aiming at reducing the processing requirements at the DU located close to the antenna. Even though functional split has been standardized and evaluated for terrestrial networks, its applicability in NTN has not been discussed up to now. Functional split is expected to be part of 3GPP NTN Rel-19, where regenerative payload is expected to be introduced in a new working item at the time of writing this paper. This work evaluates the different split options in NTN for low earth orbit (LEO) satellites based on NTN key performance indicators (KPIs) and highlights the challenges that hinders the implementation of functional splits in NTN. A new architecture is proposed to facilitate the implementation of functional splits in NTN while gaining the desired advantages compared to a transparent payload or a full gNB onboard.
Evaluation of New Radio Beam Management Framework for LEO Satellites
Xavier, A., & Miguel Ángel Vázquez
This work reviews the beam management framework of New Radio, identifies the challenges to be addressed for a proper operation in non-terrestrial network and numerically evaluates its suitability for satellite beam selection, satellite tracking and satellite acquisition in the case of LEO constellations. It reveals that satellite beam selection and satellite tracking can be performed efficiently, while acquisition times are in the range of a few to tenths of seconds, in the case that no GNSS and ephemeris information is exploited, as considered in future 3GPP releases towards 6G. These delays may be acceptable for a pure initial acquisition, but new solutions are needed for efficient satellite handovers or idle mode operation.
Flexible Synchronous Federated Learning Approach for LEO Satellite Constellation Networks
Madyan Alsenwi, Eva Lagunas, Jorge Querol, Mohammed Al-Ansi and Symeon Chatzinotas
This paper presents a flexible synchronous federated learning (FlexSync-FL) approach for Low Earth Orbit (LEO) satellite constellation networks, where LEO satellites train local models and conduct a collaborative global model at the Network Operations Center (NOC). Unlike the standard synchronous FL, FlexSync-FL employs a dual-trigger synchronization mechanism that initiates global model aggregation either upon receiving updates from all clients (satellites) or after a predefined maximum interval time has elapsed. Furthermore, FlexSync-FL leverages inter-satellite links (ISLs) to facilitate forwarding local models among satellites, especially for those without direct visibility to ground gateway stations (GWs). In particular, FlexSync-FL aims to mitigate the impact of long latency and intermittent connectivity, inherent in satellite networks, on the FL process. The effectiveness of the proposed FlexSync-FL framework is demonstrated through simulations that employ Long ShortTerm Memory (LSTM) networks to train local models at each LEO satellite for traffic forecasting using real-world aeronautical datasets.
Robust Beamforming for Massive MIMO LEO Satellite Communications: A Risk-Aware Learning Framework
Madyan Alsenwi, Eva Lagunas and Symeon Chatzinotas
This paper proposes a robust beamforming algorithm for massive multiple-input multiple-output (MIMO) low earth-orbit (LEO) satellite communications under uncertain channel conditions. Specifically, a risk-aware optimization problem is formulated to optimize the hybrid digital and analog precoding aiming at maximizing the energy efficiency of the LEO satellite while considering the required quality-of-service (QoS) by each ground user. The Conditional Value at Risk (CVaR) is used as a risk measure of the downlink data rate to capture the high dynamic and random channel variations due to satellite movement, achieving the required QoS under the worst-case scenario. A deep reinforcement learning (DRL) based framework is developed to solve the formulated stochastic problem over time slots. Considering the limited computation capabilities of the LEO satellite, the training process of the proposed learning algorithm is performed offline at a central terrestrial server. The trained models are then sent periodically to the LEO satellite through ground stations to provide online executions on the transmit precoding based on the current network state. Simulation results demonstrate the efficacy of the proposed approach in achieving the QoS requirements under uncertain wireless channel conditions.
Learning-Based Traffic Scheduling in Non-Stationary Multipath 5G Non-Terrestrial Networks
Machumilane, A.; Gotta, A.; Cassará, P.; Amato, G.; Gennaro, C.
In non-terrestrial networks, where low Earth orbit satellites and user equipment move relative to each other, line-of-sight tracking and adapting to channel state variations due to endpoint movements are a major challenge. Therefore, continuous line-of-sight estimation and channel impairment compensation are crucial for user equipment to access a satellite and maintain connectivity. In this paper, we propose a framework based on actor-critic reinforcement learning for traffic scheduling in non-terrestrial networks scenario where the channel state is non-stationary due to the variability of the line of sight, which depends on the current satellite elevation. We deploy the framework as an agent in a multipath routing scheme where the user equipment can access more than one satellite simultaneously to improve link reliability and throughput. We investigate how the agent schedules traffic in multiple satellite links by adopting policies that are evaluated by an actor-critic reinforcement learning approach. The agent continuously trains its model based on variations in satellite elevation angles, handovers, and relative line-of-sight probabilities. We compare the agent’s retraining time with the satellite visibility intervals to investigate the effectiveness of the agent’s learning rate. We carry out performance analysis while considering the dense urban area of Paris, where high-rise buildings significantly affect the line of sight. The simulation results show how the learning agent selects the scheduling policy when it is connected to a pair of satellites. The results also show that the retraining time of the learning agent is up to 0.1𝑡𝑖𝑚𝑒𝑠 the satellite visibility time at given elevations, which guarantees efficient use of satellite visibility.
TRANTOR Maritime Dataset
Shahid, H., Miguel Ángel Vázquez, Henarejos, P.
Dataset of maritime traffic.
