面向天地融合网络的无线资源智能分配方法Intelligent Allocation Method of Radio Resource for Integrated Space-ground Network
魏强,廖瑛,徐潇审,郝媛媛,任术波,张千,缪中宇,辛宁
摘要(Abstract)：
为满足天地融合网络全时、全域通信需求，采用认知无线电技术可实现有限频谱资源的感知与高效利用，有效缓解同频干扰问题。文章提出了一种用于天地一体认知网络的信道选择和功率调整的无线资源智能分配方法，在保证主用户服务质量的前提下最大化系统数据速率。首先，将天地融合网络建模为异质图结构，通过用户距离估计信道状态信息，并且利用图卷积网络提取和分析关键环境特征。其次，采用深度强化学习探索底层拓扑环境信息，通过试错与奖惩机制不断优化资源分配策略。仿真结果验证了所提方法的收敛性，并且证明系统数据速率能够得到显著提升。
关键词(KeyWords)： 天地融合网络;认知无线电;频谱感知;图卷积网络;深度强化学习;频谱管理;同频干扰
基金项目(Foundation): 2022YFB2902700
作者(Author): 魏强,廖瑛,徐潇审,郝媛媛,任术波,张千,缪中宇,辛宁
参考文献(References)：
- [1] 吴巍.天地一体化信息网络发展综述[J].天地一体化信息网络，2020,1(1):1-16.WU Wei.Survey on the development of space-integrated-ground information network [J].Space-Integrated-Ground Information Networks,2020,1(1):1-16 (in Chinese).
- [2] 张晓凯，郭道省，张邦宁.空天地一体化网络研究现状与新技术的应用展望[J].天地一体化信息网络，2021,2(4):19-26.ZHANG Xiaokai,GUO Daoxing,ZHANG Bangning.Research status of space-air-ground integrated network and application prospects of new technologies [J].Space-Integrated-Ground Information Networks,2021,2(4):19-26 (in Chinese).
- [3] 刘瑞，朱诗兵，李长青，等.认知卫星通信频谱感知及资源分配技术综述[J].电讯技术，2021,61(8):1048-1058.LIU Rui,ZHU Shibing,LI Changqing,et al.Review of spectrum sensing and resource allocation in cognitive satellite communication [J].Telecommunication Engineering,2021,61(8):1048-1058 (in Chinese).
- [4] GüR G.Spectrum sharing and content-centric operation for 5G hybrid satellite networks:prospects and challenges for space-terrestrial system integration [J].IEEE Vehicular Technology Magazine,2019,14(4):38-48.
- [5] JIA M,GU X,GUO Q,et al.Broadband hybrid satellite-terrestrial communication systems based on cognitive radio toward 5G [J].IEEE Wireless Communications,2016,23(6):96-106.
- [6] ZHANG Y,SHI Y,SHEN F,et al.Satellite-terrestrial spectrum sensing scheme based on cascaded FNN and FIS [C]//IEEE.Proceedings of 2019 IEEE Globecom Workshops.New York:IEEE,2019:1-6.
- [7] ZHANG X,JIA M,GU X,et al.Intelligent spectrum management based on radio map for cloud-based satellite and terrestrial spectrum shared networks [J].China Communications,2021,18(12):108-118.
- [8] JIANG F,ZHANG L,SUN C,et al.Clustering and resource allocation strategy for D2D multicast networks with machine learning approaches [J].China Communications,2021,18(1):196-211.
- [9] KAUR A,KUMAR K.Energy-efficient resource allocation in cognitive radio networks under cooperative multi-agent model-free reinforcement learning schemes [J].IEEE Transactions on Network and Service Ma nagement,2020,17(3):1337-1348.