Bho Matthiesen

Sourav Mukherjee, Bho Matthiesen, Armin Dekorsy et al.

Future 6G networks are envisioned to integrate low Earth orbit satellite mega-constellations to enable seamless global connectivity, particularly in underserved and remote areas. However, the deployment of dense mega-constellations introduces interference among satellites operating over shared frequency bands. This represents a rather new setup for studying spectrum sharing, which exacerbates the limited flexibility of conventional FDD systems based on fixed bands for downlink and uplink transmissions. We address this spectrum-sharing problem and propose dynamic re-assignment of FDD bands for improved interference management in dense deployments, as well as evaluate the performance gain of this approach. To this end, we formulate a joint optimization problem that incorporates dynamic band assignment, user scheduling, and power allocation in both directions. This non-convex mixed integer problem is solved using a combination of equivalence transforms, alternating optimization, and state-of-the-art industrial-grade mixed integer solvers. Numerical results demonstrate that the proposed approach of dynamic FDD band assignment significantly enhances system performance over conventional FDD, achieving up to 30\% improvement in throughput in dense deployments.

Bho Matthiesen, Nasrin Razmi, Israel Leyva-Mayorga et al.

Federated learning (FL) has recently emerged as a distributed machine learning paradigm for systems with limited and intermittent connectivity. This paper presents the new context brought to FL by satellite constellations, where the connectivity patterns are significantly different from the ones observed in conventional terrestrial FL. The focus is on large constellations in low Earth orbit (LEO), where each satellites participates in a data-driven FL task using a locally stored dataset. This scenario is motivated by the trend towards mega constellations of interconnected small satellites in LEO and the integration of artificial intelligence in satellites. We propose a classification of satellite FL based on the communication capabilities of the satellites, the constellation design, and the location of the parameter server. A comprehensive overview of the current state-of-the-art in this field is provided and the unique challenges and opportunities of satellite FL are discussed. Finally, we outline several open research directions for FL in satellite constellations and present some future perspectives on this topic.

Nasrin Razmi, Bho Matthiesen, Armin Dekorsy et al.

Federated learning in satellite constellations, where the satellites collaboratively train a machine learning model, is a promising technology towards enabling globally connected intelligence and the integration of space networks into terrestrial mobile networks. The energy required for this computationally intensive task is provided either by solar panels or by an internal battery if the satellite is in Earth's shadow. Careful management of this battery and system's available energy resources is not only necessary for reliable satellite operation, but also to avoid premature battery aging. We propose a novel energy-aware computation time scheduler for satellite FL, which aims to minimize battery usage without any impact on the convergence speed. Numerical results indicate an increase of more than 3x in battery lifetime can be achieved over energy-agnostic task scheduling.

Sourav Mukherjee, Nasrin Razmi, Armin Dekorsy et al.

This paper investigates federated learning (FL) in a multi-hop communication setup, such as in constellations with inter-satellite links. In this setup, part of the FL clients are responsible for forwarding other client's results to the parameter server. Instead of using conventional routing, the communication efficiency can be improved significantly by using in-network model aggregation at each intermediate hop, known as incremental aggregation (IA). Prior works [1] have indicated diminishing gains for IA under gradient sparsification. Here we study this issue and propose several novel correlated sparsification methods for IA. Numerical results show that, for some of these algorithms, the full potential of IA is still available under sparsification without impairing convergence. We demonstrate a 15x improvement in communication efficiency over conventional routing and a 11x improvement over state-of-the-art (SoA) sparse IA.

Nasrin Razmi, Bho Matthiesen, Armin Dekorsy et al.

Mega-constellations of small satellites have evolved into a source of massive amount of valuable data. To manage this data efficiently, on-board federated learning (FL) enables satellites to train a machine learning (ML) model collaboratively without having to share the raw data. This paper introduces a scheme for scheduling on-board FL for constellations connected with intra-orbit inter-satellite links. The proposed scheme utilizes the predictable visibility pattern between satellites and ground station (GS), both at the individual satellite level and cumulatively within the entire orbit, to mitigate intermittent connectivity and best use of available time. To this end, two distinct schedulers are employed: one for coordinating the FL procedures among orbits, and the other for controlling those within each orbit. These two schedulers cooperatively determine the appropriate time to perform global updates in GS and then allocate suitable duration to satellites within each orbit for local training, proportional to usable time until next global update. This scheme leads to improved test accuracy within a shorter time.

Nasrin Razmi, Bho Matthiesen, Armin Dekorsy et al.

In Low Earth Orbit (LEO) mega constellations, there are relevant use cases, such as inference based on satellite imaging, in which a large number of satellites collaboratively train a machine learning model without sharing their local datasets. To address this problem, we propose a new set of algorithms based on Federated learning (FL), including a novel asynchronous FL procedure based on FedAvg that exhibits better robustness against heterogeneous scenarios than the state-of-the-art. Extensive numerical evaluations based on MNIST and CIFAR-10 datasets highlight the fast convergence speed and excellent asymptotic test accuracy of the proposed method.

Bho Matthiesen, Alessio Zappone, Karl-L. Besser et al.

This work develops a novel power control framework for energy-efficient power control in wireless networks. The proposed method is a new branch-and-bound procedure based on problem-specific bounds for energy-efficiency maximization that allow for faster convergence. This enables to find the global solution for all of the most common energy-efficient power control problems with a complexity that, although still exponential in the number of variables, is much lower than other available global optimization frameworks. Moreover, the reduced complexity of the proposed framework allows its practical implementation through the use of deep neural networks. Specifically, thanks to its reduced complexity, the proposed method can be used to train an artificial neural network to predict the optimal resource allocation. This is in contrast with other power control methods based on deep learning, which train the neural network based on suboptimal power allocations due to the large complexity that generating large training sets of optimal power allocations would have with available global optimization methods. As a benchmark, we also develop a novel first-order optimal power allocation algorithm. Numerical results show that a neural network can be trained to predict the optimal power allocation policy.