Deep Reinforcement Learning for the Agile Earth Observation Satellite Scheduling Problem
Mathematics · 25.09.2023 · 11 (19) · 4059
DOI: 10.3390/math11194059 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 25.09.2023. Verfasst von Jie Chun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Young Elite Scientists Sponsorship Program by CAST, Hunan Postgraduate Research Innovation Project.
Abstract (Originalsprache)
The agile earth observation satellite scheduling problem (AEOSSP) is a combinatorial optimization problem with time-dependent constraints. Recently, many construction heuristics and meta-heuristics have been proposed; however, existing methods cannot balance the requirements of efficiency and timeliness. In this paper, we propose a graph attention network-based decision neural network (GDNN) to solve the AEOSSP. Specifically, we first represent the task and time-dependent attitude transition constraints by a graph. We then describe the problem as a Markov decision process and perform feature engineering. On this basis, we design a GDNN to guide the construction of the solution sequence and train it with proximal policy optimization (PPO). Experimental results show that the proposed method outperforms construction heuristics at scheduling profit by at least 45%. The proposed method can also calculate the approximate profits of the state-of-the-art method with an error of less than 7% and reduce scheduling time markedly. Finally, we demonstrate the scalability of the proposed method.
Förderung
- National Natural Science Foundation of China
- Young Elite Scientists Sponsorship Program by CAST
- Hunan Postgraduate Research Innovation Project
Zitieren
APA
Chun, J., Yang, W., Liu, X., Wu, G., He, L., & Xing, L. (2023). Deep Reinforcement Learning for the Agile Earth Observation Satellite Scheduling Problem. Mathematics, 11(19), 4059. https://doi.org/10.3390/math11194059
Vancouver
Chun J, Yang W, Liu X, Wu G, He L, Xing L. Deep Reinforcement Learning for the Agile Earth Observation Satellite Scheduling Problem. Mathematics. 2023;11(19):4059. doi:10.3390/math11194059
BibTeX
@article{Chun2023,
author = {Chun, Jie and Yang, Wenyuan and Liu, Xiaolu and Wu, Guohua and He, Lei and Xing, Lining},
title = {Deep Reinforcement Learning for the Agile Earth Observation Satellite Scheduling Problem},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {19},
pages = {4059},
doi = {10.3390/math11194059}
}
EUVIMED