高速移动环境下基于DQN的毫米波MISO系统下行链路波束成形
DQN based Beamforming optimization for highly-mobile MISO downlink system
投稿时间:2020-12-17  修订日期:2020-12-17
DOI:
中文关键词: 波束成形  JB-PCIC  DQN  SINR  速率和容量
英文关键词: beamforming  JB-PCIC  DQN  SINR  sum rate capacity
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);
作者单位E-mail
李中捷 中南民族大学 电子信息工程学院 lizhongjie@mail.scuec.edu.cn 
吴园君 中南民族大学 电子信息工程学院 wuyuanjun1111@163.com 
金闪 中南民族大学 电子信息工程学院  
钟小辉 中南民族大学 电子信息工程学院  
摘要点击次数: 23
全文下载次数: 0
中文摘要:
      针对高速移动环境下毫米波MISO系统的可靠性通信问题,本文提出一种基于深度Q网络(deep Q network, DQN)的下行链路波束成形优化方案.该方案首先根据用户高速移动导致的多普勒频移构建高速移动毫米波信道模型;然后结合功率控制和干扰约束,将MISO系统下行链路的波束成形联合设计方案(joint beamforming,power Control and interference coordination, JB-PCIC)建模为非凸优化问题;最后根据最大化信干噪比(signal to interference plus noise ratio, SINR)及用户的位置坐标,构建智能体-无线环境交互,利用DQN的贪婪属性估计动作的未来奖励,求解该优化问题.仿真结果表明,与穷举搜索的最优算法相比,本文提出的基于DQN算法的JB-PCIC方案在显著降低复杂度的情况下,可以达到穷举最优算法的速率和容量.
英文摘要:
      In order to solve the reliability communication problem of mmWave MISO system in highly-mobile environment, this paper proposes an optimization approach for downlink beamforming based on Deep Q network. Firstly, the paper constructs highly-mobile mmWave channel model according to the Doppler frequency shift caused by the high-speed movement of users, and then formulates the joint design of beamforming, power control, and interference coordination as a non-convex optimization problem in MISO downlink system; finally, according to the signal to interference plus noise ratio (SINR) and the user’s location coordinates, the agent-environment interaction is constructed, and by using the greedy nature of DQN to estimate the future reward of the action to solve the optimization problem. The simulation indicated that the proposed JB-PCIC algorithm based on DQN can achieve comparable performance with respect to exhaustive search while operating at much lower complexity.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭