Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Communications in computer and information science

Satellite Constellation Scheduling with Quantum Reinforcement Learning

Gyu Seon Kim, Samuel Yen-Chi Chen, Soohyun Park, Joongheon Kim

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.1007/978-981-95-7829-0_6

Related papers

Scheduling of Satellite Constellation Operations in EO Missions Using Quantum Optimization

Vinicius Marchioli, Mattia Boggio, Deborah Volpe +2 more

Communications in computer and information science•Jan 1, 2024•9 citations

Dynamic Resource Allocation for LEO Satellite Quantum Networks using Deep Reinforcement Learning

Phuc Hao

•Jan 1, 2025•0 citations

Deep Learning-Based Secure Scheduling and Cooperative Artificial Noise Generation in LEO Satellite Networks

Yongjae Lee, Taehoon Kim, Inkyu Bang +2 more

As key enablers of 6G, low Earth orbit (LEO) satellite constellations are expected to offer global and low-latency connectivity. However, the broadcast nature and open-space propagation of satellite communications make it inherently vulnerable to eavesdropping. In dense LEO constellations where multiple satellites simultaneously cover overlapping regions, satellite scheduling can significantly contribute to secrecy performance. In this letter, we investigate a novel deep learning-based secure scheduling problem for physical layer security (PLS) in LEO satellite networks. During the scheduling process, we jointly consider multi-satellite transmission and cooperative artificial noise (AN) generation to defend against eavesdropping. The proposed deep learning-based scheduler, designed using attention-based permutation-invariant neural networks, learns security-oriented scheduling policies based solely on statistical channel information of eavesdroppers. Simulation results demonstrate that the proposed scheduling algorithm significantly enhances secrecy performance in terms of both secrecy rate and secrecy outage probability, outperforming conventional baseline schemes.

IEEE Wireless Communications Letters•Jan 1, 2026•1 citation

QUARGS - Quantum Reinforced Ground Station Scheduling

Daniel Alexander Leidreiter, Andreas Petrak, Michael Alexander Anderle +1 more

Consider a constellation of n satellites in medium-earth orbit as well as k ground stations distributed over the Earth. Such satellites require semiregular contacts with mission control in order to upload telecommands or general purpose maintenances, which is done via ground stations. In order to plan ground station contacts for such a constellation it is necessary to calculate possible visibilities between satellite--ground station pairs, and then build a valid schedule from that data which satisfies all mission-specific constraints. This is a typical challenge for the mission planning system of a satellite constellation. In addition, there is often some kind of relevant optimization goal, for example fairness conditions or minimization of total number of contacts to have more time available for the actual missions objectives. Depending on the constraints for such ground station contact plans as well as the size of n and k, this problem may be hard to solve optimally. In particular, if k is much smaller than n it may be non-trivial to find any solution at all. For such problems one often employs global optimizers such as Gurobi, CPLEx or SCIP, or problem-specific heuristic search algorithms that try to find a solution that is good enough for practical purposes. While such approaches can be made to work for most real scenarios, classical solvers tend to struggle to find solutions in a reasonable time for very large satellite constellations. Due to this reason, we investigate potential applications of quantum computers to larger instances of this problem in this paper. To this end, we developed a library called QUARGS (Quantum Reinforced Ground Station Scheduling) which allows solving examples for such ground station scheduling problems using different quantum algorithms. In this paper we compare and evaluate these different solutions against each other as well as against a classical solution using the global optimizer SCIP. After an overview of similar problems in the literature we define the concrete problem including all constraints as well as possible optimization functions. Then we give a brief overview of quantum algorithms that may be used to solve such scheduling problems. This includes in particular quantum annealing (QA), quantum approximate optimization algorithm (QAOA), variational quantum eigensolvers (VQE), as well as evolutionary variational quantum eigensolvers (E-VQE). The latter in particular was implemented and published in an open-source Python library QUEASARS (Quantum Evolving Ansatz Variational Solver). Besides evaluating these algorithms on sample cases regarding their solution quality and quantum circuit depths, we discuss difficulties for the implementation of various constraints in the algorithms and their potential solutions.

•Jan 1, 2025•0 citations

Quantum Reinforcement Learning for Coordinated Satellite Systems

Gyu Seon Kim, Samuel Yen-Chi Chen, Soohyun Park +1 more

Reinforcement learning (RL) using conventional neural networks (NN) has significantly progressed in various applications. However, conventional RL needs help training in environments with large-scale action dimensions, such as coordinated mobility/satellite systems. Quantum reinforcement learning (QRL) with quantum NN (QNN) can address this problem through superposition and entanglement, one of the great features of quantum mechanics. Based on its ‘i) fast convergence’ and ‘ii) high scalability’, unique advantages of QRL that distinguish it from conventional RL, this paper highlights the potential for QRL utilization in coordinated mobility and satellite systems.

IEEE International Conference on Acoustics Speech and Signal Processing•Mar 12, 2025•13 citations

Towards Large-Scale Satellite Acquisition Scheduling with Hybrid Quantum-Classical Optimization

Amer Delilbasic, Morris Riedel, Kristel F. L. Michielsen +1 more

Communications in computer and information science•Jan 1, 2026•1 citation
As key enablers of 6G, low Earth orbit (LEO) satellite constellations are expected to offer global and low-latency connectivity. However, the broadcast nature and open-space propagation of satellite communications make it inherently vulnerable to eavesdropping. In dense LEO constellations where multiple satellites simultaneously cover overlapping regions, satellite scheduling can significantly contribute to secrecy performance. In this letter, we investigate a novel deep learning-based secure scheduling problem for physical layer security (PLS) in LEO satellite networks. During the scheduling process, we jointly consider multi-satellite transmission and cooperative artificial noise (AN) generation to defend against eavesdropping. The proposed deep learning-based scheduler, designed using attention-based permutation-invariant neural networks, learns security-oriented scheduling policies based solely on statistical channel information of eavesdroppers. Simulation results demonstrate that the proposed scheduling algorithm significantly enhances secrecy performance in terms of both secrecy rate and secrecy outage probability, outperforming conventional baseline schemes.
Consider a constellation of n satellites in medium-earth orbit as well as k ground stations distributed over the Earth. Such satellites require semiregular contacts with mission control in order to upload telecommands or general purpose maintenances, which is done via ground stations. In order to plan ground station contacts for such a constellation it is necessary to calculate possible visibilities between satellite--ground station pairs, and then build a valid schedule from that data which satisfies all mission-specific constraints. This is a typical challenge for the mission planning system of a satellite constellation. In addition, there is often some kind of relevant optimization goal, for example fairness conditions or minimization of total number of contacts to have more time available for the actual missions objectives. Depending on the constraints for such ground station contact plans as well as the size of n and k, this problem may be hard to solve optimally. In particular, if k is much smaller than n it may be non-trivial to find any solution at all. For such problems one often employs global optimizers such as Gurobi, CPLEx or SCIP, or problem-specific heuristic search algorithms that try to find a solution that is good enough for practical purposes. While such approaches can be made to work for most real scenarios, classical solvers tend to struggle to find solutions in a reasonable time for very large satellite constellations. Due to this reason, we investigate potential applications of quantum computers to larger instances of this problem in this paper. To this end, we developed a library called QUARGS (Quantum Reinforced Ground Station Scheduling) which allows solving examples for such ground station scheduling problems using different quantum algorithms. In this paper we compare and evaluate these different solutions against each other as well as against a classical solution using the global optimizer SCIP. After an overview of similar problems in the literature we define the concrete problem including all constraints as well as possible optimization functions. Then we give a brief overview of quantum algorithms that may be used to solve such scheduling problems. This includes in particular quantum annealing (QA), quantum approximate optimization algorithm (QAOA), variational quantum eigensolvers (VQE), as well as evolutionary variational quantum eigensolvers (E-VQE). The latter in particular was implemented and published in an open-source Python library QUEASARS (Quantum Evolving Ansatz Variational Solver). Besides evaluating these algorithms on sample cases regarding their solution quality and quantum circuit depths, we discuss difficulties for the implementation of various constraints in the algorithms and their potential solutions.
Reinforcement learning (RL) using conventional neural networks (NN) has significantly progressed in various applications. However, conventional RL needs help training in environments with large-scale action dimensions, such as coordinated mobility/satellite systems. Quantum reinforcement learning (QRL) with quantum NN (QNN) can address this problem through superposition and entanglement, one of the great features of quantum mechanics. Based on its ‘i) fast convergence’ and ‘ii) high scalability’, unique advantages of QRL that distinguish it from conventional RL, this paper highlights the potential for QRL utilization in coordinated mobility and satellite systems.