基于图学习的密集空间网络传输资源调度方法
Graph Learning Based Transmission Resources Scheduling in Dense Space Networks
- 电子学报 2021年49卷第11期 页码：2133-2137
- 作者机构：
1.西安建筑科技大学信息与控制工程学院，陕西西安 710055
2.西安电子科技大学综合业务网理论及关键技术国家重点实验室，陕西西安 710071
- 作者简介：
[ "刘润滋 女，1988年生，山东潍坊人.现为西安建筑科技大学信息与控制工程学院副教授，主要研究方向为无线自组织网络、空间信息网络智能组网技术等.E-mail:rzliu@xauat.edu.cn" ]
[ "吴伟华（通信作者） 男，1988年生，河北石家庄人.现为西安电子科技大学通信工程学院讲师，主要研究方向为无线通信网络、资源管理方法设计、随机网络优化等.E-mail:whwu@xidian.edu.cn" ]
- 基金信息：国家自然科学基金(61701365;61801365;62001347);中国博士后科学基金(2018M643581;2019TQ0241;2020M673344);陕西省重点研发计划(2021GY-066);陕西省自然科学基金(2020JQ-686);陕西省高校科协青年人才托举计划基金(20200112);陕西省博士后科研基金(2018BSHEDZZ47)
DOI：10.12263/DZXB.20201217
中图分类号： TN919;TN927收稿：2020-10-30，
修回：2021-07-08，
纸质出版：2021-11-25
- 稿件说明：
移动端阅览
刘润滋,吴伟华,张文柱等.基于图学习的密集空间网络传输资源调度方法[J].电子学报,2021,49(11):2133-2137.
LIU Run-zi,WU Wei-hua,ZHANG Wen-zhu,et al.Graph Learning Based Transmission Resources Scheduling in Dense Space Networks[J].ACTA ELECTRONICA SINICA,2021,49(11):2133-2137.
刘润滋,吴伟华,张文柱等.基于图学习的密集空间网络传输资源调度方法[J].电子学报,2021,49(11):2133-2137. DOI： 10.12263/DZXB.20201217.
LIU Run-zi,WU Wei-hua,ZHANG Wen-zhu,et al.Graph Learning Based Transmission Resources Scheduling in Dense Space Networks[J].ACTA ELECTRONICA SINICA,2021,49(11):2133-2137. DOI： 10.12263/DZXB.20201217.
摘要
面对密集空间网络传输资源调度问题中的复杂度以及有效性挑战，本文以图论模型为纽带，将传统数学模型与机器学习方法相结合，提出一种基于图学习的密集空间网络传输资源调度方法.该方法基于图论模型对问题结构的认知将密集空间网络资源调度问题分解，由数学模型与基于图结构的强化学习交替配合完成整个求解过程.实验结果表明，与传统的基于数学模型的资源调度方法相比，所提方法能将资源调度收益提升25.1%，且其训练结果对网络场景变化具有较好的适应性.
Abstract
Facing the challenges of the transmission resource schedule of dense space networks
we combine the mathematical models and machine learning methods
and propose a graph learning based approach for the scheduling of transmission resources in dense space networks. In the proposed method
transmission resource scheduling problem is decomposed based on the knowledge of the problem structure brought by graph theory. On this basis
mathematical model and reinforcement learning alternately complete the whole solution process. Simulation results show that
compared with the traditional mathematical model-based methods
the proposed method improves the scheduling profits by 25.1%
and its training results have better generality.
关键词
Keywords
references
Zhang Z , Zhang W , Tseng F H . Satellite mobile edge computing: Improving QoS of high-speed satellite-terrestrial networks using edge computing techniques [J]. IEEE Network , 2019 , 33 ( 1 ): 70 - 76 .
姜会林 , 付强 , 赵义武 , 刘显 著. 空间信息网络与激光通信发展现状及趋势 [J]. 物联网学报 , 2019 , 3 ( 2 ): 1 - 8 .
Jiang H L , Fu Q , Zhao Y W , LIU X Z . Development status and trend of space information network and laser communication [J]. Chinese Journal on Internet of Things , 2019 , 3 ( 2 ): 1 - 8 . (in Chinese)
Rojanasoonthon S , Bard J . A GRASP for parallel machine scheduling with time windows [J]. INFORMS Journal on Computing , 2005 , 17 ( 1 ): 32 - 51 .
Wang L , Jiang C , Kuang L , et al . Mission scheduling in space network with antenna dynamic setup times [J]. IEEE Transactions on Aerospace and Electronic Systems , 2019 , 55 ( 1 ): 31 - 45 .
Baek S , Han S , Cho K , et al . Development of a scheduling algorithm and GUI for autonomous satellite missions [J]. Acta Astronautica , 2011 , 68 ( 7-8 ): 1396 - 1402 .
Barbulescu L , Watson J P , Whitley L D , et al . Scheduling space-ground communications for the air force satellite control network [J]. Journal of Scheduling , 2004 , 7 ( 1 ): 7 - 34 .
Chen M , Challita U , Saad W , et al . Artificial neural networks-based machine learning for wireless networks: A tutorial [J]. IEEE Communications Surveys & Tutorials , 2019 , 21 ( 4 ): 3039 - 3071 .
Liang L , Ye H , Yu G , et al . Deep-learning-based wireless resource allocation with application to vehicular networks [J]. Proceedings of the IEEE , 2019 , 108 ( 2 ): 341 - 356 .
Sun H , Chen X , Shi Q , et al . Learning to optimize: Training deep neural networks for interference management [J]. IEEE Transactions on Signal Processing , 2018 , 66 ( 20 ): 5438 - 5453 .
Deng B , Jiang C , Yao H , et al . The next generation heterogeneous satellite communication networks: Integration of resource management and deep reinforcement learning [J]. IEEE Wireless Communications , 2019 , 27 ( 2 ): 105 - 111 .
Meng X , Wu L , Yu S . Research on resource allocation method of space information networks based on deep reinforcement learning [J]. Remote Sensing , 2019 , 11 ( 4 ): 448 .
Qiu C , Yao H , Yu F R , et al . Deep q-learning aided networking, caching, and computing resources allocation in software-defined satellite-terrestrial networks [J]. IEEE Transactions on Vehicular Technology , 2019 , 68 ( 6 ): 5871 - 5883 .
Song B , Yao F , Chen Y , et al . A hybrid genetic algorithm for satellite image downlink scheduling problem [J]. Discrete Dynamics in Nature and Society , 2018 : 1531452 .
0
浏览量
15
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies