An energy-efficient learning solution for the Agile Earth Observation Satellite Scheduling Problem
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep Reinforcement LearningEarth ObservationSchedulingSimilar Papers 제목 키워드 기반
Multi-strip observation scheduling problem for ac-tive-imaging agile earth observation satellites
Active-imaging agile earth observation satellite (AI-AEOS) is a new generation agile earth observation satellite (AEOS). With renewed capabilities in observation and active im-aging, AI-AEOS improves upon the observation…
Earth ObservationSchedulingThree multi-objective memtic algorithms for observation scheduling problem of active-imaging AEOS
Observation scheduling problem for agile earth observation satellites (OSPFAS) plays a critical role in management of agile earth observation satellites (AEOSs). Active imaging enriches the extension of OSPFAS, we call t…
Earth ObservationManagementSchedulingAgile Earth observation satellite scheduling over 20 years: formulations, methods and future directions
Agile satellites with advanced attitude maneuvering capability are the new generation of Earth observation satellites (EOSs). The continuous improvement in satellite technology and decrease in launch cost have boosted th…
Earth ObservationSchedulingEOS-Bench: A Comprehensive Benchmark for Earth Observation Satellite Scheduling
Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While next-generation agile Earth observation satellites (EOS) increase oper…
Computational EfficiencyReinforcement LearningA Constraint Programming Model for the Super-Agile Earth Observation Satellite Imaging Scheduling Problem
As the dependence on satellite imaging continues to grow, modern satellites have become increasingly agile, with the new generation, namely super-agile Earth observation satellites (SAEOS), providing unprecedented imagin…