李中捷,吴婉敏,高伟.基于深度学习的D2D毫米波通信中继选择[J].中南民族大学学报自然科学版,2020,39(3):283-288
基于深度学习的D2D毫米波通信中继选择
Relay selection based on deep learning for D2D millimeter wave communication
  
DOI:10.12130/znmdzk.20200311
中文关键词: D2D通信  中继选择  深度学习  卷积神经网络  能量效率
英文关键词: D2D  relay selection  deep learning  CNN  energy efficiency
基金项目:国家自然科学基金资助项目(61379028,61671483);湖北省自然科学基金资助项目(2016CFA089);中央高校基本科研业务费专项资金资助(CZY19003)
作者单位
李中捷 中南民族大学 电信学院武汉430074 
吴婉敏 中南民族大学 电信学院武汉430074 
高伟 中南民族大学 电信学院武汉430074 
摘要点击次数: 413
全文下载次数: 223
中文摘要:
      针对毫米波(mm wave)环境下,设备到设备(D2D)直接通信链路遇到阻碍时的中继选择问题,提出一种基于深度学习的解决方案.采用卷积神经网络(CNN)框架构建能够成功决策和精确预测的智能模型,并基于能量效率最大准则,实现最优化D2D中继链路选择.仿真实验采用毫米波多天线MIMO数据集对所提模型进行了训练和测试.仿真结果表明,提出的基于深度学习的中继选择方案在吞吐量和能量效率方面优于常用的基于快速频率切换的解决方案.
英文摘要:
      Aiming at the problem of relay selection when the device-to-device (D2D) direct communication link encounters obstacles in the millimeter wave environment, a solution based on deep learning is proposed . The solution adopts a Convolutional Neural Network (CNN) framework to build an intelligent model, capable of successful decision-making and accurate prediction. Based on the maximum energy efficiency criterion, the most optimized D2D relay link selection is achieved. The simulation experiment uses the deep-MIMO dataset of millimeter wave multi-antenna MIMO to train and test the model proposed. Simulation results show that the relay selection scheme based on deep learning proposed is superior to the more commonly used fast frequency switching based solutions in terms of throughput and energy efficiency.
查看全文   查看/发表评论  下载PDF阅读器
关闭