Energy Efficient Client Selection in Federated Learning for Orbital Edge Computing

Low Earth Orbit (LEO) satellite constellations provide a wide range of services such as communications, earth observation, signal monitoring, and scientific missions. While these constellations generate valuable data, transferring it to ground stations (GS) for machine learning-based analysis presents significant challenges due to downlink bandwidth and energy constraints. Federated Learning (FL) integrated with Orbital Edge Computing (OEC) has been explored as a solution to these challenges. This paper presents FedSCS (Satellite Client Selection), a novel energy-efficient and decentralised FL framework designed to optimise communication with GSs and minimise energy consumption. FedSCS selects satellites (clients) based on their available resources and utilises reinforcement learning for cluster formation. The performance evaluation conducted under the Walker Delta-based LEO constellation across various datasets reveals that FedSCS can sustain high accuracy while considerably reducing training time and energy consumption. FedSCS achieves a notable reduction in energy consumption of 6.67%, 10.34%, and 9.09% compared to the recently developed FedOrbit on the MNIST, CIFAR-10, and EuroSat datasets, while also achieving a slight improvement in accuracy.