An Application of Online Learning to Spacecraft Memory Dump Optimization
This addresses a domain-specific problem for space operations by providing a practical optimization method for satellite memory management.
The paper tackled spacecraft memory dump optimization by applying online learning with expert advice to real data from the Copernicus Sentinel-6 satellite, resulting in a lightweight Follow-The-Leader algorithm that increased performance by over 60% compared to traditional techniques.
In this paper, we present a real-world application of online learning with expert advice to the field of Space Operations, testing our theory on real-life data coming from the Copernicus Sentinel-6 satellite. We show that in Spacecraft Memory Dump Optimization, a lightweight Follow-The-Leader algorithm leads to an increase in performance of over $60\%$ when compared to traditional techniques.