Generalized Model and Deep Reinforcement Learning-Based Evolutionary Method for Multitype Satellite Observation Scheduling

Generalized Model and Deep Reinforcement Learning-Based Evolutionary Method for Multitype Satellite Observation Scheduling

Song, Yanjie (Xidian University)
Ou, Junwei (Xiangtan University, Xiangtan)
Pedrycz, Witold (University of Alberta; Polish Academy of Sciences; Istinye University)
Suganthan, Ponnuthurai Nagaratnam (Qatar University)
Wang, X. (TU Delft Learning & Autonomous Control)
Xing, Lining (Xidian University)
Zhang, Yue (Beihang University)

2024

Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications due to its ability to cope with various complex situations. In the multitype satellite observation scheduling problem (MTSOSP), the constraints involved in different types of satellites make the problem challenging. This article proposes a mixed-integer programming model and a generalized profit representation method in the model to effectively cope with the situation of multiple types of satellite observations. To obtain a suitable observation plan, a deep reinforcement learning-based genetic algorithm (DRL-GA) is proposed by combining the learning method and genetic algorithm. The DRL-GA adopts a solution generation method to obtain the initial population and assist with local search. In this method, a set of statistical indicators that consider resource utilization and task arrangement performance are regarded as states. By using deep neural networks to estimate the <inline-formula> <tex-math notation="LaTeX">$Q$</tex-math> </inline-formula> value of each action, this method can determine the preferred order of task scheduling. An individual update strategy and an elite strategy are used to enhance the search performance of DRL-GA. Simulation results verify that DRL-GA can effectively solve the MTSOSP and outperforms the state-of-the-art algorithms in several aspects. This work reveals the advantages of the proposed generalized model and scheduling method, which exhibit good scalability for various types of observation satellite scheduling problems.

Combinatorial optimization problem
deep reinforcement learning (DRL)
Earth Observing System
evolutionary algorithm (EA)
generalized model
Genetic algorithms
multitype
Optimization
satellite observation
Satellites
scheduling
Sociology
Statistics
Task analysis

http://resolver.tudelft.nl/uuid:24e4ed3c-9dc2-4405-9b87-ba9d9588f02b

https://doi.org/10.1109/TSMC.2023.3345928

2024-07-15

2168-2216

IEEE Transactions on Systems, Man, and Cybernetics: Systems, 54 (4), 2576-2589

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2024 Yanjie Song, Junwei Ou, Witold Pedrycz, Ponnuthurai Nagaratnam Suganthan, X. Wang, Lining Xing, Yue Zhang