Scheduling for Ground-Assisted Federated Learning in LEO Satellite Constellations
Nasrin Razmi, Bho Matthiesen, Armin Dekorsy, Petar Popovski
Abstract
Distributed training of machine learning models directly on satellites in low Earth orbit (LEO) is considered. Based on a federated learning (FL) algorithm specifically targeted at the unique challenges of the satellite scenario, we design a scheduler that exploits the predictability of visiting times between ground stations (GS) and satellites to reduce model staleness. Numerical experiments show that this can improve the convergence speed by a factor three.
Topics & Concepts
Computer sciencePredictabilitySatelliteConstellationScheduling (production processes)ExploitLow earth orbitSatellite constellationConvergence (economics)Federated learningSatellite broadcastingDistributed computingReal-time computingAerospace engineeringComputer securityMathematical optimizationEngineeringPhysicsAstronomyMathematicsEconomic growthQuantum mechanicsEconomicsSatellite Communication SystemsAge of Information OptimizationOptimization and Search Problems