Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling
Agile Earth observation satellite scheduling is crucial for space-based remote-sensing services. The sharply rising demands and explosion of the solution space pose significant challenges to the optimization of observation task scheduling. To address this issue, we propose a deep reinforcement learn...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/23/4436 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850106744759386112 |
|---|---|
| author | Dongning Liu Guanghui Zhou |
| author_facet | Dongning Liu Guanghui Zhou |
| author_sort | Dongning Liu |
| collection | DOAJ |
| description | Agile Earth observation satellite scheduling is crucial for space-based remote-sensing services. The sharply rising demands and explosion of the solution space pose significant challenges to the optimization of observation task scheduling. To address this issue, we propose a deep reinforcement learning-based attention decision network (ADN) to determine the task scheduling sequence. We also construct a Markov decision process model in which the original and direct attributes are defined to describe the environment and used as the input of the ADN. Moreover, a start-time-shift-based local search is proposed to improve the observation plan generated by the ADN model. A comprehensive experiment was conducted, and the results proved that the attention mechanism in our ADN was beneficial for the training process to converge to better strategies. Compared with other advanced algorithms, the proposed method obtained a better total profit in the test sets. Furthermore, our methods exhibit considerable time efficiency, even for large-scale problems. |
| format | Article |
| id | doaj-art-aecff7ddf11647aab9b721ea29e8bcf7 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-aecff7ddf11647aab9b721ea29e8bcf72025-08-20T02:38:45ZengMDPI AGRemote Sensing2072-42922024-11-011623443610.3390/rs16234436Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite SchedulingDongning Liu0Guanghui Zhou1School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, ChinaAgile Earth observation satellite scheduling is crucial for space-based remote-sensing services. The sharply rising demands and explosion of the solution space pose significant challenges to the optimization of observation task scheduling. To address this issue, we propose a deep reinforcement learning-based attention decision network (ADN) to determine the task scheduling sequence. We also construct a Markov decision process model in which the original and direct attributes are defined to describe the environment and used as the input of the ADN. Moreover, a start-time-shift-based local search is proposed to improve the observation plan generated by the ADN model. A comprehensive experiment was conducted, and the results proved that the attention mechanism in our ADN was beneficial for the training process to converge to better strategies. Compared with other advanced algorithms, the proposed method obtained a better total profit in the test sets. Furthermore, our methods exhibit considerable time efficiency, even for large-scale problems.https://www.mdpi.com/2072-4292/16/23/4436earth observationschedulingattention networkdeep reinforcement learninglocal search |
| spellingShingle | Dongning Liu Guanghui Zhou Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling Remote Sensing earth observation scheduling attention network deep reinforcement learning local search |
| title | Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling |
| title_full | Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling |
| title_fullStr | Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling |
| title_full_unstemmed | Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling |
| title_short | Deep Reinforcement Learning-Based Attention Decision Network for Agile Earth Observation Satellite Scheduling |
| title_sort | deep reinforcement learning based attention decision network for agile earth observation satellite scheduling |
| topic | earth observation scheduling attention network deep reinforcement learning local search |
| url | https://www.mdpi.com/2072-4292/16/23/4436 |
| work_keys_str_mv | AT dongningliu deepreinforcementlearningbasedattentiondecisionnetworkforagileearthobservationsatellitescheduling AT guanghuizhou deepreinforcementlearningbasedattentiondecisionnetworkforagileearthobservationsatellitescheduling |