摘要
动态频谱共享被认为是解决未来5G/6G复杂网络环境“频谱赤字危机”这一问题直接有效的手段之一。然而,由于5G/6G网络超密集、高异构、高动态、智能化的新特征,频谱共享发现(频谱感知)面临着海量数据获取成本高、价值密度低、检测结果不准确、机会发现不充分等问题与挑战,基于机器学习的动态频谱高效感知成为电磁频谱领域重要的研究方向。首先分析了电磁频谱动态共享的国家战略需求和技术挑战,然后从动态频谱信息的联合稀疏采样、协同感知、多维协同预测三方面介绍了国内外研究现状和发展动态,提出了动态频谱高效感知的核心科学问题;最后给出了问题解决思路,为实现未来复杂无线网络频谱高效利用提供理论和使能技术支撑。
Dynamic spectrum sharing has been recognized as one of the most direct and efficient methods to solve the issue of ever-increasing serious spectrum deficit risk in future broadband mobile communication systems(5G&6G).However,due to the potential new features of future 5G&6G networks,including densification,high hyper-heterogeneity,high dynamics,and intelligence,there are new problems and new challenges faced by the discovery process of spectrum sharing(namely spectrum sensing),such as the huge gathering cost of spectrum big data,low valued data density,inaccurate detection outputs,insufficient sharing opportunity discovery,etc.Dynamic spectrum efficient sensing technology based on machine learning has become an important research direction in electromagnetic spectrum field.Firstly,the national strategic demands and technical challenges of dynamic spectrum sharing are investigated.Then,the present domestic and foreign research and related developments on three aspects are summarized,including joint sparse sampling,cooperative sensing,multi-dimensional collaborative prediction.At the same time,the core scientific problems of dynamic spectrum efficient perception are proposed.Finally,the solving approaches of the problems are given,which can be employed to significantly improve the spectrum utilization in future complex wireless networks.
作者
崔翠梅
殷昌永
杨德智
CUI Cuimei;YIN Changyong;YANG Dezhi(School of Electrical and Information Engineering,Changzhou Institute of Technology,Changzhou 213032,China;National Mobile Communications Research Laboratory,Southeast University,Nanjing 211189,China;ZTE Corporation,Shanghai 201203,China)
出处
《电讯技术》
北大核心
2025年第4期634-641,共8页
Telecommunication Engineering
基金
国家自然科学基金面上项目(62371075,62372070)
国家自然科学基金青年基金项目(61801056)
中国博士后科学基金(2018M632203)
江苏省教育厅未来网络研究基金(FNSRFP-2021-YB-37)
江苏高校"青蓝工程"中青年学术带头人培养对象人才资助项目。
关键词
复杂网络
动态频谱共享
高效感知
多维协同预测
联合稀疏采样
机器学习
complex network
dynamic spectrum sharing
efficient sensing
multi-dimensional collaborative prediction
joint sparse sampling
machine learning
作者简介
通信作者:崔翠梅,女,1978年生于江苏徐州,2015年获博士学位,现为副教授,主要研究方向为认知无线网络、智能无线通信理论与关键技术,Email:nicolec2008@126.com;殷昌永,男,1973年生于江苏盐城,2007年获硕士学位,现为副教授、高级工程师,主要研究方向为智能检测计算;杨德智,男,1993年生于江苏徐州,2021年获硕士学位,现为高级工程师,主要研究方向为认知无线电、运营商承载网络。
