Orbit-Aware Split Learning: Optimizing LEO Satellite Networks for Distributed Online Learning

This paper proposes a split learning (SL) framework tailored for Low Earth Orbit (LEO) satellite constellations, leveraging their cyclical movement to improve energy efficiency. Although existing research focuses on offloading tasks to the non-terrestrial network (NTN) infrastructure, these approaches overlook the dynamic movement patterns of LEO satellites that can be used to efficiently distribute the learning task. In this work, we analyze how LEO satellites, from the perspective of ground terminals, can participate in a time-window-based model training. By splitting the model between a LEO and a ground terminal, the computational burden on the satellite segment is reduced, while each LEO satellite offloads the partially trained model to the next satellite in the constellation. This cyclical training process allows larger and more energy-intensive models to be deployed and trained across multiple LEO satellites, despite their limited energy resources. We formulate an optimization problem that manages radio and processing resources, ensuring the entire data is processed during each satellite pass while minimizing the energy consumption. Results demonstrate that the proposed architecture optimizes both communication and processing resources, achieving up to 97% energy savings compared to direct raw data transmission. This approach offers a more scalable and energy-efficient way to train complex models, enhancing the capabilities of LEO satellite constellations in Artificial Intelligence-driven applications.