认知无线电是一种可用于有效缓解当前频谱资源紧张的技术，而频谱感知是认知无线电的前提。针对低信噪比情况下频谱感知性能差的问题，提出一种将信号高阶统计量、协方差矩阵特征值与神经网络相结合的合作频谱感知算法。该算法考虑到认知用户与授权用户的信道衰落情况，利用神经网络较强的多分类能力，将最大-最小特征值之比、平均-最小特征值之比以及高阶统计量作为特征参数，通过神经网络实现合作频谱感知。仿真结果表明，该算法不仅在低信噪比情况下较其他算法具有更高的频谱检测率，而且对频谱中信号的调制类型也有较高的识别率。
Cognitive radio is a technology that can be used to effectively alleviate the current strain of spectrum resources, and spectrum sensing is the prerequisite of cognitive radio. To overcome the poor performance under the condition of low SNR, a cooperative spectrum sensing algorithm combining the high-order cumulants of signal and the eigenvalue of covariance matrix with the neural network is proposed. The algorithm takes into account the channel fading between the cognitive users and primary users and utilizes the strong multi-classification ability of neural networks. The ratio of maximum-minimum eigenvalues, the ratio of average-minimum eigenvalues, and high-order cumulants are used as the inputs of neural networks to realize the spectrum sensing. The simulation results show that the proposed algorithm not only has higher spectrum detection rate than other algorithms at low SNR, but also identifies the modulation type of the signal.
[1] Haykin S. Cognitive radio:brain-empowered[J]. IEEE Journal on Selected Areas in Communications,2005, 23(2):201-220.
[2] Jiang C X, Zhang H J, Ren Y, et al. Machine learning paradigms for next-generation wireless networks[J]. IEEE Wireless Communications,2017,24(2):98-105.
[3] Khan A A, Rehmani M H, Reisslein M. Cognitive radio for smart grids:survey of architectures, spectrum sensing mechanisms, and networking protocols[J]. IEEE Communications Surveys and Tutorials, 2016, 18(1):860-898.
[4] Atapattu S, Tellambura C. Energy detection based cooperative spectrum sensing in cognitive radio networks[J]. IEEE Transactions on Wireless Communications, 2010,8(12):5761-5766.
[5] Awe O P, Zhu Z M, Lambotharan S. Eigenvalue and support vector machine techniques for spectrum sensing in cognitive radio networks[C]//The 2013 Conference on Technologies and Applications of Artificial Intelligence(TAAI). Taipei:IEEE Press,2013:223-227.
[6] 王鑫, 汪晋宽, 刘志刚, 等. 基于随机森林的认知网络频谱感知算法[J]. 仪器仪表学报,2013,34(11):2471-2488.
[7] Tang Y J, Zhang Q Y, Lin W. Artificial neural network based spectrum sensing method for cognitive radio[C]//6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM). Chengdu:IEEE Press, 2010:1-4.
[8] 赵春晖,杨伟超,马爽.基于广义二阶循环统计量的通信信号调制识别研究[J]. 通信学报,2011,32(1):144-150.
[9] 刘明骞,李兵兵,曹超凤,等. 认知无线电中非高斯噪声下数字调制信号识别方法[J].通信学报,2014, 35(1):82-88.
[10] Yang F, Li Z, Zeng S. A novel method for wireless communication signal modulation recognition in smart grid[J]. Journal of Communications, 2016,11(9):813-818.
[11] Zeng Y H, Liang Y C. Eigenvalue-based spectrum sensing algorithms for cognitive radio[J]. IEEE Transactions on Communications, 2009, 57(6):1784-1793.
[12] 弥寅, 卢光跃.基于特征值极限分布的合作频谱感知[J].通信学报,2015,36(1):84-89.
