Data-driven Onboard Scheduling for an Autonomous Observation Satellite

Chao Li, Yingwu Chen, Patrick De Causmaecker

Abstract: Observation requests for autonomous observation satellites are dynamically generated. Considering the limited computing resources, a data-driven onboard scheduling method combining AI techniques and polynomial-time heuristics is proposed in this work. To construct observation schedules, a framework with offline learning and onboard scheduling is adopted. A neural network is trained offline in ground stations to assign the scheduling priority to observation requests in the onboard scheduling, based on the optimized historical schedules obtained by genetic algorithms which are computationally demanding to run onboard. The computational simulations show that the performance of the scheduling heuristic is enhanced using the data-driven framework.