An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem
This addresses energy efficiency and image quality issues for satellite operators, representing a strong domain-specific improvement.
The paper tackles the Agile Earth Observation Satellite Scheduling Problem by developing a Deep Reinforcement Learning approach that optimizes target selection and observation timing to reduce energy waste and improve image quality. Results show a >60% reduction in poor-quality image capture and up to 78% decrease in energy waste from attitude maneuvers.
The Agile Earth Observation Satellite Scheduling Problem (AEOSSP) entails finding the subset of observation targets to be scheduled along the satellite's orbit while meeting operational constraints of time, energy and memory. The problem of deciding what and when to observe is inherently complex, and becomes even more challenging when considering several issues that compromise the quality of the captured images, such as cloud occlusion, atmospheric turbulence, and image resolution. This paper presents a Deep Reinforcement Learning (DRL) approach for addressing the AEOSSP with time-dependent profits, integrating these three factors to optimize the use of energy and memory resources. The proposed method involves a dual decision-making process: selecting the sequence of targets and determining the optimal observation time for each. Our results demonstrate that the proposed algorithm reduces the capture of images that fail to meet quality requirements by > 60% and consequently decreases energy waste from attitude maneuvers by up to 78%, all while maintaining strong observation performance.