基于深度学习的动态主用户频谱感知算法
电子技术应用
李新玉1,赵知劲1,2
1.杭州电子科技大学 通信工程学院,浙江 杭州 310018; 2.中国电子科技集团第36研究所 通信系统信息控制技术国家级重点实验室,浙江 嘉兴 314001
摘要: 实际的频谱感知场景中主用户可能随机到达或者离开,当主用户状态在实时频谱感知期间动态变化时,现有的静态频谱感知算法性能急剧恶化。针对该现状,研究提出基于残差收缩注意力机制的动态主用户频谱感知算法。频谱感知间隔内,主用户随机到达或者随机离开的时间服从均匀分布。采用深度残差收缩网络(DRSN)提取动态主用户特征,并且滤除冗余的噪声特征;利用协调注意力模块(CAM)增强每个通道不同方向的特征信息,提高模型对动态主用户特征的表达能力。仿真结果表明,所提算法性能优于对比算法ResNet、CBAM_IQ和CBAM_Energy,所提算法对主用户随机到达或者离开服从不同分布的主用户都可以保持较高的检测概率。
中圖分類號:TN925 文獻標志碼:A DOI: 10.16157/j.issn.0258-7998.234333
中文引用格式: 李新玉,趙知勁. 基于深度學習的動態(tài)主用戶頻譜感知算法[J]. 電子技術應用,2024,50(1):60-65.
英文引用格式: Li Xinyu,Zhao Zhijin. Dynamic primary user spectrum sensing algorithm based on deep learning[J]. Application of Electronic Technique,2024,50(1):60-65.
中文引用格式: 李新玉,趙知勁. 基于深度學習的動態(tài)主用戶頻譜感知算法[J]. 電子技術應用,2024,50(1):60-65.
英文引用格式: Li Xinyu,Zhao Zhijin. Dynamic primary user spectrum sensing algorithm based on deep learning[J]. Application of Electronic Technique,2024,50(1):60-65.
Dynamic primary user spectrum sensing algorithm based on deep learning
Li Xinyu1,Zhao Zhijin1,2
1.School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China; 2.National Key Laboratory of Communication System Information Control Technology, 36th Research Institute of China Electronics Technology Group, Jiaxing 314001, China
Abstract: In actual spectrum sensing scenarios, the primary user may arrive or leave randomly, and when the primary user state changes dynamically during real-time spectrum sensing, the performance of the existing static spectrum sensing algorithm deteriorates sharply. For this situation, this paper propose a dynamic primary user spectrum sensing algorithm based on the residual shrinkage and attention mechanism. During the spectrum-sensing interval, the time when the primary user randomly arrives or leaves randomly follows a uniform distribution. The “deep residual shrinkage network (DRSN)” is used to extract dynamic primary user features and filter out redundant noise features. The “coordination attention module (CAM)” is used to improve the ability of the model to express the features of the dynamic primary user. Simulation results show that the proposed algorithm performs are better than ResNet algorithm, CBAM_IQ algorithm and CBAM_Energy algorithm. The proposed algorithm can maintain a high detection probability for the primary users who randomly arrive or leave following different distributions.
Key words : cognitive radio;spectrum sensing;dynamic primary user;deep residual contraction network;coordinated attention mechanism
引言
隨著5G通信技術的發(fā)展和無線通信業(yè)務的飛速增長,頻譜資源處于供不應求的狀態(tài)。認知無線電(Cognitive Radio, CR)[1]的提出緩解了頻譜資源緊張的局面,頻譜感知(Spectrum Sensing, SS)[2]是認知無線電的關鍵技術,它允許次用戶(Secondary User, SU)使用空閑的授權頻譜。靜態(tài)主用戶(Primary User ,PU)的頻譜感知算法已經(jīng)得到深入研究,靜態(tài)主用戶是指感知階段主用戶狀態(tài)保持不變,即始終活躍或者始終沉默,而實際場景中,感知過程中主用戶可能隨機到達或者隨機離開。當主用戶狀態(tài)發(fā)生變化時,頻譜感知算法性能會受到影響。因此,研究在感知期間主用戶的狀態(tài)發(fā)生變化的頻譜感知算法具有很強的實際意義。
本文詳細內容請下載:
http://m.ihrv.cn/resource/share/2000005836
作者信息:
李新玉1,趙知勁1,2
(1.杭州電子科技大學 通信工程學院,浙江 杭州 310018;
2.中國電子科技集團第36研究所 通信系統(tǒng)信息控制技術國家級重點實驗室,浙江 嘉興 314001)

此內容為AET網(wǎng)站原創(chuàng),未經(jīng)授權禁止轉載。
