A new data-driven task planning approach for on-orbit refueling of low-earth orbit mega-constellation members

doi:10.23919/JSEE.2026.000143

Abstract

Abstract:

On-orbit refueling for low-Earth orbit (LEO) mega-constellations requires solving complex access sequence problems. The increasing number of satellites complicates finding optimal solutions. To tackle this, we introduce a data-driven enhanced ant colony optimization (DDEACO) method in this paper. DDEACO uses a two-step approach: initially, it trains a deep Q-network (DQN) using the $\Delta V$ transfer cost as a reward and employs gated recurrent units (GRUs) to learn Q values for selecting the optimal next satellite member for visitation, capturing the sequences’ temporal dependencies. Then, it integrates the pre-trained GRU with traditional ant colony optimization (ACO) to offer new heuristic paths, improving ACO’s exploration and efficiency. The effectiveness of DDEACO is demonstrated through numerical experiments on systems tool kit (STK)-generated datasets with 30 satellites and 200 satellites, showing its significant performance.

Key words: task planning, low-Earth orbit (LEO) mega-constellation, metaheuristic algorithm, reinforcement learning, on-orbit refueling

Xingping Huang, Shi Qiu, Haotian Zhao, Ming Liu, Xibin Cao. A new data-driven task planning approach for on-orbit refueling of low-earth orbit mega-constellation members[J]. Journal of Systems Engineering and Electronics, 2026, 37(4): 1354-1363.

Figures/Tables 11

Fig 1

Fig 2

Fig 3

Fig 4

Table 1

Fig 5

Fig 6

Fig 7

Fig 8

Table 2

Fig 9

References 33

1	Zhang J R, Cai Y F, Xue C B, et al LEO mega constellations: review of development, impact, surveillance, and governance. Space: Science & Technology, 2022, 2022, 9865174.
2	Li W J, Cheng D Y, Liu X G, et al On-orbit service (OOS) of spacecraft: a review of engineering developments. Progress in Aerospace Sciences, 2019, 108, 32. doi: 10.1016/j.paerosci.2019.01.004
3	Liu A R, Xu X L, Xiong Y Q, et al Maneuver strategies of starlink satellite based on SpaceX-released ephemeris. Advances in Space Research, 2024, 74 (7): 3157. doi: 10.1016/j.asr.2024.06.038
4	Du B X, Zhao Y, Dutta A, et al Optimal scheduling of multispacecraft refueling based on cooperative maneuver. Advances in Space Research, 2015, 55 (12): 2808. doi: 10.1016/j.asr.2015.02.025
5	Liang W K, Zhi H, Han P, et al GEO satellite on-orbit refueling and debris removal hybrid mission planning under uncertainty. Advances in Space Research, 2024, 74 (5): 2376. doi: 10.1016/j.asr.2024.05.059
6	Lu L H Multi-path allocation scheduling optimization algorithm for network data traffic based on SDN architecture. IMA Journal of Mathematical Control and Information, 2020, 37 (4): 1237. doi: 10.1093/imamci/dnaa011
7	Askarirobati G H, Borzabadi A H, Heydari A Solving multiobjective optimal control problems using an improved scalarization method. IMA Journal of Mathematical Control and Information, 2020, 37 (4): 1524. doi: 10.1093/imamci/dnaa023
8	Souzban M, Solaymani F O, Borzabadi A H A rapid-based improvement on some mesh refinement strategies in solving optimal control problems. IMA Journal of Mathematical Control and Information, 2020, 37 (2): 395.
9	Alfriend K T, Lee D J, Creamer N G Optimal Servicing of Geosynchronous Satellites. Journal of Guidance, Control, and Dynamics, 2006, 29 (1): 203. doi: 10.2514/1.15602
10	Izzo D, Getzner I, Hennes D, et al. Evolving solutions to TSP variants for active space debris removal [C]// Annual Conference on Genetic and Evolutionary Computation, 2015: 1207.
11	Madakat D, Morio J, Vanderpooten D Biobjective planning of an active debris removal mission. Acta Astronautica, 2013, 84, 182. doi: 10.1016/j.actaastro.2012.10.038
12	Xu Y J, Liu X L, He R J, et al Active debris removal mission planning method based on machine learning. Mathematics, 2023, 11 (6): 1419. doi: 10.3390/math11061419
13	Li H Y, Baoyin H X Optimization of multiple debris removal missions using an evolving elitist club algorithm. IEEE Trans. on Aerospace and Electronic Systems, 2019, 56 (1): 773.
14	Hu Q L, Shao X D, Guo L. Data-driven adaptive control for spacecraft constrained reorientation [C]//Intelligent Autonomous Control of Spacecraft with Multiple Constraints, 2023: 65.
15	Hu Q L, Shao X D, Guo L. I&I adaptive pose control of spacecraft under kinematic and dynamic constraints[C]//Intelligent Autonomous Control of Spacecraft with Multiple Constraints. Singapore: Springer Nature, 2023: 233.
16	Chonghui G, Yuchang L, Huanwen T Modified evolutionary algorithm for global optimization. Journal of Systems Engineering and Electronics, 2004, 15 (1): 1.
17	Das S, Suganthan P N Differential evolution: a survey of the state-of-the-art. IEEE Trans. on Evolutionary Computation, 2011, 15 (1): 4. doi: 10.1109/TEVC.2010.2059031
18	Zhuoran Z, Changqiang H, Hanqiao H, et al An optimization method: hummingbirds optimization algorithm. Journal of Systems Engineering and Electronics, 2018, 29 (2): 386. doi: 10.21629/JSEE.2018.02.19
19	Tong S, Qu H, Xue J J K-DSA for the multiple traveling salesman problem. Journal of Systems Engineering and Electronics, 2023, 34 (6): 1614.
20	Yu N K, Qian B, Hu R, et al Solving open vehicle problem with time window by hybrid column generation algorithm. Journal of Systems Engineering and Electronics, 2022, 33 (4): 997. doi: 10.23919/JSEE.2022.000096
21	Meng X H, Li J, Zhou M C, et al Population-based incremental learning algorithm for a serial colored traveling salesman problem. IEEE Trans. on Systems, Man, and Cybernetics: Systems, 2018, 48 (2): 277. doi: 10.1109/TSMC.2016.2591267
22	Muarkami J, Hokamoto S. Approach for optimal multi-rendezvous trajectory design for active debris removal[C]//61st International Astronautical Congress, 2010: 6013.
23	Liu Y, Yang J N, Wang Y Z, et al Multi-objective optimal preliminary planning of multi-debris active removal mission in LEO. Science China Information Sciences, 2017, 60, 072202.
24	Guo J, Pang Z J, Du Z H. Optimal planning for a multi-debris active removal mission with a partial debris capture strategy[J]. Chinese Journal of Aeronautics, 2023, 36(6): 256.
25	Kong L J, Zhou Y Multiobjective mission planning for multiple geosynchronous spacecraft refueling. International Journal of Aerospace Engineering, 2023, 2023 (1): 6623461. doi: 10.1155/2023/6623461
26	Zhou Y, Yan Y, Huang X, et al Optimal scheduling of multiple geosynchronous satellites refueling based on a hybrid particle swarm optimizer. Aerospace Science and Technology, 2015, 47, 125. doi: 10.1016/j.ast.2015.09.024
27	Wang Q L, Gao X Z, Wang C H, et al Hybrid anti-prematuration optimization algorithm. Journal of Systems Engineering and Electronics, 2010, 21 (3): 503. doi: 10.3969/j.issn.1004-4132.2010.03.023
28	Cui X X, Li Q, Qing T Genetic algorithm for pareto optimum-based route selection. Journal of Systems Engineering and Electronics, 2007, 18 (2): 360. doi: 10.1016/S1004-4132(07)60099-1
29	Zhao Z, Zhang J, Li H Y, et al LEO cooperative multi-spacecraft refueling mission optimization considering J2 perturbation and target’s surplus propellant constraint. Advances in Space Research, 2017, 59 (1): 252. doi: 10.1016/j.asr.2016.10.005
30	Li C Z, Xu B Optimal scheduling of multiple Sun-synchronous orbit satellites refueling. Advances in Space Research, 2020, 66 (2): 345. doi: 10.1016/j.asr.2020.03.049
31	Petropoulos A, Grebow D, Jones D, et al. GTOC9: methods and results from the Jet Propulsion Laboratory team[C]//31st International Symposium on Space Technology and Science, 2017. https://www.researchgate.net/publication/317232050.
32	Wang L, Zhu Y L. A new inversion-free iterative algorithm for the discrete algebraic Riccati equation [J]. IMA Journal of Mathematical Control and Information, 2024, 41(1): 149.
33	Zhang L P, Zhang G S Cooperative optimal control for descriptor multi-agent systems. IMA Journal of Mathematical Control and Information, 2020, 37 (3): 935. doi: 10.1093/imamci/dnz035

Parameter	Dataset I	Dataset II
Number of satellites	30	200
Orbital altitude h/km	800—1000	900—1100
Orbital Inclination i/(°)	98.854—99.489	88.743—89.519
RAAN $\varOmega $/(°)	152.368—287.519	149.224—282.781

Algorithm	Optimal $\Delta V$/(m/s)		Time complexity	Space complexity	Algorithm type
Algorithm	Dataset I	Dataset II	Time complexity	Space complexity	Algorithm type
DQN	505.58	3994.79	$O(N + {N^2})$	$O({N^2})$	Reinforcement learning
A3C	611.54	3753.04	$O(N + {N^2})$	$O({N^2})$	Reinforcement learning
MCTS	148.0	10962.0	−	−	Random search
GA	460.69	3470.82	$O(N)$	$O(N + {N^2})$	Metaheuristic
ABC	172.51	602.64	$O({N^2})$	$O(N + {N^2})$	Metaheuristic
QPSO	476.33	3582.46	$O(N)$	$O(N)$	Metaheuristic
AFSA	238.27	2416.59	$O(N)$	$O(N)$	Metaheuristic
PSO	271.26	2537.65	$O(N\log N)$	$O(N + {N^2})$	Metaheuristic
ACO	80.17	108.54	$O({N^2})$	$O(N + {N^2})$	Metaheuristic
MMAS	159.17	161.47	$O({N^2})$	$O({N^2})$	Metaheuristic
SSA	188.32	2854.43	$O(N + N\log N)$	$O(N)$	Metaheuristic
DDEACO	80.17	84.0	$O(N + {N^2})$	$O({N^2})$	Data-driven enhanced metaheuristic

[1]	Shijun Xie, Hao Liang, Liping Li, Jintian Xiong, Sili Liu. Design and optimization for polar coded cooperative transmission in satellite-based NTN [J]. Journal of Systems Engineering and Electronics, 2026, 37(4): 1177-1185.
[2]	Yuanyuan Nie, Zhigeng Fang, Su Gao, Jiajia Cai. Reinforcement survivable routing for resource-limited LEO satellite network [J]. Journal of Systems Engineering and Electronics, 2026, 37(4): 1341-1353.
[3]	Jingbo WANG, Liaoyuan ZHU, Shaojie XIA, Huibin LIU, Jing LIU, Chongxiao QU, Zhihuan SONG. Application of self-play reinforcement learning and explainable decision tree in intelligent air combat [J]. Journal of Systems Engineering and Electronics, 2026, 37(2): 616-635.
[4]	Xiaoyu XING, Haoxiang XIA. A formation pursuit method integrated coordinated reciprocity for enhanced capture [J]. Journal of Systems Engineering and Electronics, 2026, 37(1): 211-224.
[5]	Shijie DENG, Yingxin KOU, Maolong LYU, Zhanwu LI, An XU. λ-return-based aircraft maneuvering for terminal defense and positioning guidance strategies [J]. Journal of Systems Engineering and Electronics, 2025, 36(6): 1692-1708.
[6]	Wenhao CHEN, Gang CHEN, Jichao LI, Jiang JIANG. Disintegration of heterogeneous combat network based on double deep Q-learning [J]. Journal of Systems Engineering and Electronics, 2025, 36(5): 1235-1246.
[7]	Rui ZHOU, Weichao ZHONG, Wenlong LI, Hao ZHANG. Self-play training and analysis for GEO inspection game with modular actions [J]. Journal of Systems Engineering and Electronics, 2025, 36(5): 1353-1373.
[8]	Siyu HENG, Ting CHENG, Zishu HE, Yuanqing WANG, Luqing LIU. Adaptive dwell scheduling based on Q-learning for multifunctional radar system [J]. Journal of Systems Engineering and Electronics, 2025, 36(4): 985-993.
[9]	Yifan ZHANG, Tao DONG, Zhihui LIU, Shichao JIN. Multi-QoS routing algorithm based on reinforcement learning for LEO satellite networks [J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 37-47.
[10]	Nanxun DUO, Qinzhao WANG, Qiang LYU, Wei WANG. Tactical reward shaping for large-scale combat by multi-agent reinforcement learning [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1516-1529.
[11]	Guofei LI, Shituo LI, Bohao LI, Yunjie WU. Deep reinforcement learning guidance with impact time control [J]. Journal of Systems Engineering and Electronics, 2024, 35(6): 1594-1603.
[12]	Qi WANG, Zhizhong LIAO. Computational intelligence interception guidance law using online off-policy integral reinforcement learning [J]. Journal of Systems Engineering and Electronics, 2024, 35(4): 1042-1052.
[13]	Guang ZHAN, Kun ZHANG, Ke LI, Haiyin PIAO. UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience [J]. Journal of Systems Engineering and Electronics, 2024, 35(3): 644-665.
[14]	Jinming LIU, Yingguo CHEN, Rui WANG, Yingwu CHEN. Complex task planning method of space-aeronautics cooperative observation based on multi-layer interaction [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1550-1564.
[15]	Yaozhong ZHANG, Zhuoran WU, Zhenkai XIONG, Long CHEN. A UAV collaborative defense scheme driven by DDPG algorithm [J]. Journal of Systems Engineering and Electronics, 2023, 34(5): 1211-1224.