您当前访问的的浏览器版本过低,为了给您带来更好的体验,建议您升级至Edge浏览器或者推荐使用Google浏览器
取消

面向低轨卫星的频谱认知智能管控

作者:李高, 王威, 吴启晖 阅读量:705

面向低轨卫星的频谱认知智能管控

李高,王威,吴启晖
(南京航空航天大学电磁频谱空间认知动态系统工信部重点实验室,中国 南京 210016)

摘要:基于天地一体频谱资源共享面临的挑战,提出了面向低轨卫星的频谱认知智能管控体系架构。频谱感知得到三维多域频谱数据并形成频谱地理数据库;三维补全技术补全缺失的数据;频谱预测预判频谱占用情况,辅助频谱感知和决策;利用强化学习、博弈学习方式进行智能频谱决策。这样可以形成集感知、补全、预测和决策的频谱认知闭环系统,以期为后续低轨卫星频谱资源管控研究提供一些指导和建议。  
关键词:低轨卫星系统;频谱认知智能管控;频谱感知;频谱补全和预测;频谱智能决策  


Cognitive Intelligent Spectrum Management and Control for Low-Earth-Orbit Satellite Systems

LI Gao, WANG Wei, WU Qihui
(Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space, Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)

Abstract: Based on the challenges of space-air-ground spectrum sharing, a cognitive intelligent spectrum management and control architecture for low-earth-orbit (LEO) satellites is proposed. Three-dimensional multi-domain spectrum data obtained by spectrum sensing is used to form a spectrum geographic database, followed by three-dimensional completion of the missing data, and then spectrum occupancy with prediction technology is used for assisting sensing and decision-making. Reinforcement learning and game-theoretic learning methods are used for intelligent spectrum decision-making. In this way, a closed-loop of spectrum cognition based on sensing, completion, prediction and decision-making is formed, in order to provide some guidance and suggestions for the subsequent research on LEO satellite spectral resource control.
Keywords: low-earth-orbit satellite systems; cognitive intelligent management and control; spectrum sensing; spectrum completion and prediction; intelligent spectrum decision

在线PDF浏览:PDF