To address the challenges of limited satellite–ground bandwidth and heterogeneous Quality of Service (QoS) requirements for tasks in Low Earth Orbit (LEO) satellite networks, an intelligent computing-aware routing method based on task priority is proposed. First, considering satellite computing and storage resources, a resource-constrained LEO satellite network model is constructed. The sun outage phenomenon is incorporated to dynamically evaluate link availability, thereby capturing the impact of space environmental disturbances on routing decisions. Second, a QoS classification and priority scheduling mechanism is established to characterize the heterogeneous requirements of tasks in terms of latency and packet loss rate. Subsequently, a joint optimization model for computation offloading and data transmission is formulated with the objective of minimizing the end-to-end average delay. Furthermore, the optimization problem is transformed into a Markov Decision Process to enable reinforcement learning-based solutions. A task-priority queue is introduced in task processing and data forwarding, and QoS constraints are incorporated to dynamically filter candidate action space. Meanwhile, task-priority weights are embedded into the reward function. Based on these designs, a Dueling Double Deep Q-Network (Dueling-DDQN)-based computing-aware routing decision algorithm is designed to achieve adaptive optimization of computation offloading and routing decisions. Simulation results demonstrate that, under a constellation of 288 satellites, the proposed method outperforms the Proximal Policy Optimization algorithm under different traffic loads. In particular, the average end-to-end delay is reduced by 4.28%–14.53%, and the task computing ratio is increased by 1.44%–2.89%. Moreover, the proposed method maintains good applicability across different constellation scales.
[1]GHAMISI P, YOKOYA N, Li J, et al.Advances in hyperspectral image and signal processing: A comprehensive overview of the state of the art[J].IEEE Geoscience and Remote Sensing Magazine, 2017, 5(4):37-78
[2]TAO B, MASOOD M, GUPTA I, et al.Transmitting, fast and slow: Scheduling satellite traffic through space and time[C]// Proceedings of the 29th Annual International Conference on Mobile Computing and Networking. New York, NY, USA: Association for Computing Machinery, 2023: 1-15.
[3]赵艳春, 林宝军, 田丰, 等.低轨多层异构星座中低时延拓扑路由联合优化算法[J].宇航学报, 2025, 46(10):2160-2171
[4]罗宗屹, 金世超, 董涛, 等.基于的低轨卫星网络多目标智能路由算法[J].天地一体化信息网络, 2025, 6(1):16-23
[5]LIU X Y, ZHOU H B, Zhang Z T, et al.Multipath cooperative routing in ultradense LEO satellite networks: A deep-reinforcement-learning-based approach[J].IEEE Internet of Things Journal, 2025, 12(2):1789-1804
[6]李学华, 廖海龙, 张贤, 等.面向低轨卫星通信网络的联邦深度强化学习智能路由方法[J].电子与信息学报, 2025, 47(8):2652-2664
[7]唐可意, 李志刚.基于深度强化学习的低轨卫星光网络路由优化算法[J/OL]. 光通信技术, (2025-11-27) [2026-03-03]. https://link.cnki.net/urlid/45.1160.TN.20251127.1922.004. doi: 10.11959/j.issn.2096-8930.2022 033.[J].光通信技术, 2025, :-
[8]魏德宾, 操昱, 杨力, 等.唐可意, 李志刚基于深度强化学习的低轨卫星光网络路由优化算法[]光通信技术[J].航空学报, 2023, 44(16):3279941-327994111
[9]白禄鑫, 胡宇翔, 马海龙, 等.基于图强化学习的LEO卫星网络智能路由策略[J/OL].物联网学报, (2025-10-09) [2026-03-09]. https://link.cnki.net/urlid/10.1491.TP.20251009.1030.002.[J].物联网学报, 2025, :-
[10]DU X Q, NA Z Y, ZHANG N T, et al.Collaborative task offloading for LEO satellite Internet of Things: A novel computing coordinate graph-based approach[J].IEEE Systems Journal, 2025, 19(3):848-859
[11]ZHANG S B, LIU A J, HAN C, et al.GRLR: Routing with graph neural network and reinforcement learning for mega LEO satellite constellations[J].IEEE Transactions on Vehicular Technology, 2025, 74(2):3225-3237
[12]中国移动通信集团有限公司.中国移动算力网络白皮书[R/OL]. (2021-11) [2025-10-17]. https://www. digitalelite.cn/h-nd-1936.html. China Mobile Communications Group Co., Ltd. China Mobile computing force network white paper[R/OL]. (2021-11) [2025-10-17]. https://www.digitalelite.cn/h-nd-1936.html (in Chinese).[J]., 2021, :-
[13]CAO J Q, ZHANG S L, CHEN Q X, et al.Computing-aware routing for LEO satellite networks: A transmission and computation integration approach[J].IEEE Transactions on Vehicular Technology, 2023, 72(12):16607-16623
[14]LI R J, ZHU J Y, MAO Y J, et al.Topology-aware routing for federated learning over multi-layer satellite networks[C]// 2025 IEEE Wireless Communications and Networking Conference (WCNC), Milan, Italy, 2025, 1-6, doi: 10.1109/WCNC61545.2025.10978815.
[15]许柳飞, 罗志勇.面向低轨卫星网络的算力路由策略[J].移动通信, 2025, 49(6):35-42
[16]孔梦燕, 张亚生, 董飞虎.基于深度强化学习的低轨卫星网络算力路由研究[J].计算机测量与控制, 2025, 33(02):286-292
[17]JIA X, ZHOU D, SHENG M, et al.Satellite computing network construction: Optimal computing node deployment in multi-layer LEO mega-constellations[J].[J].IEEE Transactions on Communications, 2026, 74:1747-1761
[18]HAN X, XIE M, YU K, et al.Combining graph neural network with deep reinforcement learning for resource allocation in computing force networks[J].Frontiers of Information Technology & Electronic Engineering, 2024, 25(5):701-712
[19]何善琪, 罗志勇, 贺智敏.星算网络中算力均衡的智能调度方法[J].移动通信, 2025, 49(10):74-84
[20]KIM G S, LEE S, CHO I S, et al.Quantum reinforcement learning for lightweight LEO satellite routing[J].IEEE Internet of Things Journal, 2025, 12(14):28986-29004
[21]LI Y F, WANG H Q, ZHANG Z B, et al.Computing-aware routing for LEO satellite networks based on multi-step DQN[C]//2024 20th International Conference on Mobility, Sensing and Networking (MSN). 2024: 314-321.
[22]罗文, 张进, 李海阳, 等.考虑链路干扰的低轨通信星座优化设计[J].航空学报, 2026, 47(5):33219611-332196115
[23]DENG X, CHANG L, ZENG S Y, et al.Distance-based back-pressure routing for load-balancing LEO satellite networks[J].IEEE Transactions on Vehicular Technology, 2023, 72(1):1240-1253
[24]张硕, 牛庆庆, 缪馨, 等.基于马尔可夫模型的卫星网络链路通断分析与可靠路由算法研究[J].电信科学, 2025, 41(11):118-130
[25]NGUYEN L K, NGUYEN D H N, TRAN N H, et al.Deep reinforcement learning with deep double Q-network against smart jammers[C]// MILCOM 2025-2025 IEEE Military Communications Conference. Los Angeles, CA, USA: IEEE, 2025: 1524-1529.
[26]WANG Z, SCHAUL T, HESSEL M, et al.Dueling network architectures for deep reinforcement learning[C]// Proceedings of the 33rd International Conference on Machine Learning. New York, NY, USA: JMLR.org, 2016: 1995-2003.
[27]XIA S H, LUO J T, RAN Y Y.Joint optimization of computing and routing in LEO satellite constellations with distributed deep reinforcement learning[C]//2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall). Washington, DC, USA: IEEE, 2024: 1-7.
[28]SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal policy optimization algorithms[EB/.[J].rXiv:1707.06347, 2017., OL]., :-
CJA