| 45 | 0 | 9 |
| 下载次数 | 被引频次 | 阅读次数 |
低轨道地球卫星（Low Earth Orbit Satellite，LEO）通信系统凭借其广域覆盖与低时延传播特性，已成为解决偏远地区网络接入的关键技术。然而，受限于地面用户空间分布不均及业务需求的动态波动，传统静态资源分配方案难以实现波束资源的按需调度，导致系统效率低下。针对这一问题，提出基于结合优先经验回放机制的双决斗深度Q网络（Dueling Double Deep Q-Network with Prioritized Experience Replay，D3QN-PER）算法的跳波束（Beam Hopping，BH）图案优化方案。通过灵活调配有限的波束资源，实现系统平均时延最小化。仿真结果表明，与贪婪调度和轮询调度算法相比，所提方法使系统平均时延分别降低了31%和13%，显著提升了系统综合性能。
Abstract：Low Earth Orbit (LEO) satellite communication systems， owing to their wide-area coverage and low-latency propagation characteristics， have emerged as a key technology for addressing network access in remote areas. However， the uneven spatial distribution of ground users， together with the dynamic fluctuations in traffic demands， renders conventional static resource allocation schemes inadequate for on-demand scheduling of beam resources， resulting in low system efficiency. To address this issue， a beam-hopping (BH) pattern optimization scheme based on the Dueling Double Deep Q-Network with Prioritized Experience Replay (D3QN-PER) algorithm is proposed. By flexibly allocating limited beam resources， the proposed scheme aims to minimize the average delay. Simulation results demonstrate that， compared with greedy scheduling and round-robin scheduling algorithms， the proposed method reduces average delay by 31% and 13%， respectively， significantly enhancing overall system performance.
[1] 李兰兰.通感融算赋能的空天地一体化网络架构及关键技术[J].电信科学， 2025， 41(05): 29-42.
[2] 禹华钢，方子希.低轨卫星互联网：发展、应用及新技术展望[J].无线电工程， 2023， 53(11): 2699-2707.
[3] ANZALCHI J， COUCHMAN A， GABELLINI P， et al. Beam hopping in multi-beam broadband satellite systems: System simulation and performance comparison with non-hopped systems[C]//2010 5th Advanced Satellite Multimedia Systems Conference and the 11th Signal Processing for Space Communications Workshop. Cagliari， Italy: IEEE， 2010: 248-255.
[4] 汤媛媛，王珂，亢衡，等.面向空天地一体化网络的低轨星座跳波束调度技术研究[J].移动通信， 2025， 49(10): 62-73，84.
[5] YU Y， WANG Q， ZHU C， et al. Research on Communication Delay Optimization in LEO Beam Hopping Systems[C]//2024 9th International Conference on Computer and Communication Systems (ICCCS). Xi'an， China: IEEE， 2024: 752-758.
[6] ALEGRE-GODOY R， ALAGHA N， VAZQUEZ-CASTRO M A. Offered capacity optimization mechanisms for multi-beam satellite systems[C]//2012 IEEE International Conference on Communications (ICC)， Ottawa， ON， Canada: IEEE， 2012: 3180-3184.
[7] 吴翠先，董燚恒，徐勇军，等.基于不完美CSI的低轨卫星通信系统鲁棒资源分配算法[J].电子与信息学报， 2024， 46(2): 671-679.
[8] YUAN S， SUN Y， PENG M. Joint network function placement and routing optimization in dynamic software-defined satellite-terrestrial integrated networks[J]. IEEE Transactions on Wireless Communications， 2024， 23(5): 5172-5186.
[9] DENG H， YING K， FENG D， et al. Satellites beam hopping scheduling for interference avoidance[J]. IEEE Journal on Selected Areas in Communications， 2024， 42(12): 3647-3658.
[10] LIN Z， NI Z， KUANG L， et al. Multi-satellite beam hopping based on load balancing and interference avoidance for NGSO satellite communication systems[J]. IEEE Transactions on Communications， 2023， 71(1): 282-295.
[11] GAO R， WANG K， LIN W， et al. Joint beam-hopping pattern scheduling and power allocation for LEO satellite network[C]//2024 IEEE Wireless Communications and Networking Conference (WCNC). Dubai， United Arab Emirates: IEEE， 2024: 1-6.
[12] HU X， ZHANG Y， LIAO X， et al. Dynamic beam hopping method based on multi-objective deep reinforcement learning for next generation satellite broadband systems[J]. IEEE Transactions on Broadcasting， 2020， 66(3): 630-646.
[13] 刘柳，杨巧丽，梁豪，等.基于强化学习的低轨卫星跳波束资源分配策略研究[J].中国电子科学研究院学报， 2025， 20(06): 618-626.
[14] 孙天宇，袁硕，孙耀华，等.基于深度强化学习的低轨卫星跳波束资源分配方法[J/OL].无线电工程， (2026-01-08)[2026-03-11]. 1-13. https://link.cnki.net/urlid/13.1097.TN.20260108.0904.002..
[15] 刘墨添，亚森江·阿布都热合曼，潘志伟，等.基于DRL的LEO卫星波束调度与资源协同优化方法[J/OL].电讯技术， (2025-11-27)[2026-03-11]. 1-16. https://doi.org/10.20079/j.issn.1001-893x.250802001.
[16] International Telecommunication Union. Satellite antenna radiation patterns for non-geostationary orbit satellite antennas operating in the fixed-satellite service below 30 GHz: ITU-R Recommendation S.1528[S]. Geneva: ITU， 2001.
[17] European Telecommunications Standards Institute. Digital Video Broadcasting (DVB); Second Generation Framing Structure， Channel Coding and Modulation Systems for Broadcasting， Interactive Services， News Gathering and Other Broadband Satellite Applications: ETSI EN 302 307[S]. Sophia Antipolis: ETSI， 2005.
[18] WANG Z Y， SCHAUL T， HESSEL M， et al. Dueling Network Architectures for Deep Reinforcement Learning[C]//ICML'16: Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York: JMLR.org， 2015: 1995-2003.
[19] VAN HASSELT H， GUEZ A， SILVER D. Deep Reinforcement Learning with Double Q-learning[C]//AAAI Conference on Artificial Intelligence. Phoenix: AAAI， 2016: 2094-2100.
[20] SCHAUL T， QUAN J， ANTONOGLOU I， et al. Prioritized Experience Replay[EB/OL]. (2015-11-18)[2026-01-11]. https://arxiv.org/abs/1511.05952.
[21] WEN J R， WANG C， ZHAO X Y， et al. Beam Hopping and Power Allocation of LEO Multi-Satellite Communication Network Based on Multi-Agent DQN Algorithm[C]//Proceedings of the 2024 10th International Conference on Computer and Communications (ICCC). Chengdu， China: IEEE， 2024: 1832-1839.
基本信息:
中图分类号:TN927.2
引用信息:
[1]高紫梅,李伟,周平,等.基于D3QN-PER的低轨卫星跳波束资源调度策略[J].无线电工程().
2026-05-07
2026-05-07
2026-05-07