一种基于支持向量机的认知无线电频谱感知方案
|
摘要
针对以能量检测为代表的传统频谱感知算法一般存在低信噪比下性能不足,容易面临隐藏节点效应,对检测灵敏度要求高等问题,提出一种新型的基于蜂窝认知用户位置定位的频谱认知方案。该方案以无线指纹数据库为基础,通过无线指纹定位驱动认知用户实现频谱认知功能。认知用户利用无线指纹对其自身进行定位,并根据指纹数据库确定其对于授权频段接入的可能性。针对网络中的主用户发射机位置存在已知和未知2种情况,可通过认知用户读取数据库来确定授权频段可用性,或将已收集获取的历史数据作为训练数据,引入支持向量机(support vector machine,SVM)算法对认知用户所处位置的授权频段可用状态进行预测。此外,针对单个用户频谱状态预测性能不足的缺陷,提出了联合地理位置相近的多个认知用户的合作预测机制。仿真实验验证了本方案相对于传统能量检测算法的性能优势以及能效优势。
Energy detection based traditional spectrum sensing algorithms is usually subject to unsatisfactory performance at low SNR,and may even encounter hidden node effect in practice. And due to the higher sensitivity requirement,the feasibility may be problematic as well. In this paper,a novel spectrum recognition scheme on the basis of cellular cognitive secondary user positioning is proposed. Based on wireless fingerprint database,cognitive secondary users are driven by wireless fingerprint location to realize spectrum recognition function. Cognitive secondary users can use wireless fingerprint to locate themselves and determine the availability of the licensed spectrum correspondingly. Regarding that the positions of the primary user transmitters may be either known or unknown to the cognitive users,the cognitive users can make decision on the spectrum availability based on spectrum records in the database,or exploit the history spectrum data,as the training data for the support vector machine( SVM) algorithm,to make predictions of the licensed spectrum status. Furthermore,with an aim to tackle the uncertainty of single user based spectrum prediction,a joint prediction method,among multiple cognitive users within the geographical neighborhood is also proposed. Simulation results verify the superior spectrum cognition performance and energy efficiency,compared with the traditional energy detection based algorithms.
Energy detection based traditional spectrum sensing algorithms is usually subject to unsatisfactory performance at low SNR,and may even encounter hidden node effect in practice. And due to the higher sensitivity requirement,the feasibility may be problematic as well. In this paper,a novel spectrum recognition scheme on the basis of cellular cognitive secondary user positioning is proposed. Based on wireless fingerprint database,cognitive secondary users are driven by wireless fingerprint location to realize spectrum recognition function. Cognitive secondary users can use wireless fingerprint to locate themselves and determine the availability of the licensed spectrum correspondingly. Regarding that the positions of the primary user transmitters may be either known or unknown to the cognitive users,the cognitive users can make decision on the spectrum availability based on spectrum records in the database,or exploit the history spectrum data,as the training data for the support vector machine( SVM) algorithm,to make predictions of the licensed spectrum status. Furthermore,with an aim to tackle the uncertainty of single user based spectrum prediction,a joint prediction method,among multiple cognitive users within the geographical neighborhood is also proposed. Simulation results verify the superior spectrum cognition performance and energy efficiency,compared with the traditional energy detection based algorithms.
引文
[1]MITOLA J I,MARUIRE G Q J.Cognitive radio:making software radios more personal[J].IEEE Personal Communications,1999,6(4):13-18.
[2]SUN D,SONG T C,GU B,et al.Spectrum sensing and the utilization of spectrum opportunity tradeoff in cognitive radio network[J].IEEE Communications Letters,2016,20(12):2442-2445.
[3]THILINA K M,CHOI K W,SAQUIB N,et al.Machine learning techniques for cooperative spectrum sensing in cognitive radio networks[J].IEEE Journal on Selected Areas in Communications,2013,31(11):2209-2221.
[4]KHALFI B,ZAID A,HAMDAOUI B.When machine learning meets compressive sampling for wideband spectrum sensing[C]//2017 13th International Wireless Communications and Mobile Computing Conference.Valencia:IEEE Press,2017:1120-1125.
[5]GHAZIZADEH E,NIKPOUR B,MOGHADAM D A,et al.A PSO-based weighting method to enhance machine learning techniques for cooperative spectrum sensing in CR networks[C]//2016 1st Conference on Swarm Intelligence and Evolutionary Computation(CSIEC).Bam:IEEE Press,2016:113-118.
[6]FCC.In the matter of unlicensed operation in the TVbroadcast bands:second memorandum opinion and order[S].USA:FCC,2008.
[7]FCC.White space database administrators guide[S].USA:FCC,2017:45-46.
[8]Ofcom.Digital dividend:geolocation for cognitive access[S/OL].(2009-11-17)[2019-02-11].https://www.ofcom.org.uk/consultations-and-statements/category-1/cogaccess.
[9]MA Y,ZHANG X J,GAO Y.Joint sub-nyquist spectrum sensing scheme with geolocation database over TV white space[J].IEEE Transactions on Vehicular Technology,2018,67(5):3998-4007.
[10]WEI Zhiqing,FENG Zhiyong,ZHANG Qixun,et al.Three regions for space-time spectrum sensing and sccess in cognitive radio networks[J].IEEE Transactions on Vehicular Technology,2015,64(6):2448-2462.
[11]阮丽华,李勇,程伟.一种空时二维联合频谱感知区域划分方案[J].系统工程与电子技术,2016,38(5):1146-1152.RUAN Lihua,LI Yong,CHENG Wei.Novel region division approach for joint space-time spectrum 2-dimensions sensing in cognitive radio[J].Systems Engineering and Electronics,2016,38(5):1146-1152.
[12]WANG N,GAO Y,EVANS B.Database augmented spectrum sensing algorithm for cognitive radio[C]//IEEEInternational Conference on Communications.London:IEEE Press,2015:7468-7473.
[13]GUVENC I,CHONG C C.A survey on TOA based wireless localization and NLOS mitigation techniques[J].IEEE Communications Surveys&Tutorials,2009,11(3):107-124.
[14]ZHAO Lihong,ZHU Yushi,SONG Ying.Face recognition based on multi-class SVM[C]//2009 Chinese Control and Decision Conference.Guilin:IEEE Press,2009:5871-5873.
[2]SUN D,SONG T C,GU B,et al.Spectrum sensing and the utilization of spectrum opportunity tradeoff in cognitive radio network[J].IEEE Communications Letters,2016,20(12):2442-2445.
[3]THILINA K M,CHOI K W,SAQUIB N,et al.Machine learning techniques for cooperative spectrum sensing in cognitive radio networks[J].IEEE Journal on Selected Areas in Communications,2013,31(11):2209-2221.
[4]KHALFI B,ZAID A,HAMDAOUI B.When machine learning meets compressive sampling for wideband spectrum sensing[C]//2017 13th International Wireless Communications and Mobile Computing Conference.Valencia:IEEE Press,2017:1120-1125.
[5]GHAZIZADEH E,NIKPOUR B,MOGHADAM D A,et al.A PSO-based weighting method to enhance machine learning techniques for cooperative spectrum sensing in CR networks[C]//2016 1st Conference on Swarm Intelligence and Evolutionary Computation(CSIEC).Bam:IEEE Press,2016:113-118.
[6]FCC.In the matter of unlicensed operation in the TVbroadcast bands:second memorandum opinion and order[S].USA:FCC,2008.
[7]FCC.White space database administrators guide[S].USA:FCC,2017:45-46.
[8]Ofcom.Digital dividend:geolocation for cognitive access[S/OL].(2009-11-17)[2019-02-11].https://www.ofcom.org.uk/consultations-and-statements/category-1/cogaccess.
[9]MA Y,ZHANG X J,GAO Y.Joint sub-nyquist spectrum sensing scheme with geolocation database over TV white space[J].IEEE Transactions on Vehicular Technology,2018,67(5):3998-4007.
[10]WEI Zhiqing,FENG Zhiyong,ZHANG Qixun,et al.Three regions for space-time spectrum sensing and sccess in cognitive radio networks[J].IEEE Transactions on Vehicular Technology,2015,64(6):2448-2462.
[11]阮丽华,李勇,程伟.一种空时二维联合频谱感知区域划分方案[J].系统工程与电子技术,2016,38(5):1146-1152.RUAN Lihua,LI Yong,CHENG Wei.Novel region division approach for joint space-time spectrum 2-dimensions sensing in cognitive radio[J].Systems Engineering and Electronics,2016,38(5):1146-1152.
[12]WANG N,GAO Y,EVANS B.Database augmented spectrum sensing algorithm for cognitive radio[C]//IEEEInternational Conference on Communications.London:IEEE Press,2015:7468-7473.
[13]GUVENC I,CHONG C C.A survey on TOA based wireless localization and NLOS mitigation techniques[J].IEEE Communications Surveys&Tutorials,2009,11(3):107-124.
[14]ZHAO Lihong,ZHU Yushi,SONG Ying.Face recognition based on multi-class SVM[C]//2009 Chinese Control and Decision Conference.Guilin:IEEE Press,2009:5871-5873.