Optimizing Federated Learning in LEO Satellite Constellations via Intra-Plane Model Propagation and Sink Satellite Scheduling
This addresses bandwidth and connectivity issues for satellite edge computing, enabling more efficient machine learning on Earth observational data, though it is an incremental improvement over existing FL-based solutions.
The paper tackles the problem of slow convergence in federated learning for LEO satellite constellations by proposing FedLEO, which introduces intra-plane model propagation and sink satellite scheduling, resulting in drastically expedited convergence and increased model accuracy.
The advances in satellite technology developments have recently seen a large number of small satellites being launched into space on Low Earth orbit (LEO) to collect massive data such as Earth observational imagery. The traditional way which downloads such data to a ground station (GS) to train a machine learning (ML) model is not desirable due to the bandwidth limitation and intermittent connectivity between LEO satellites and the GS. Satellite edge computing (SEC), on the other hand, allows each satellite to train an ML model onboard and uploads only the model to the GS which appears to be a promising concept. This paper proposes FedLEO, a novel federated learning (FL) framework that realizes the concept of SEC and overcomes the limitation (slow convergence) of existing FL-based solutions. FedLEO (1) augments the conventional FL's star topology with ``horizontal'' intra-plane communication pathways in which model propagation among satellites takes place; (2) optimally schedules communication between ``sink'' satellites and the GS by exploiting the predictability of satellite orbiting patterns. We evaluate FedLEO extensively and benchmark it with the state of the art. Our results show that FedLEO drastically expedites FL convergence, without sacrificing -- in fact it considerably increases -- the model accuracy.