| 摘要: |
| 面向以用户为中心的无蜂窝分布式多输入多输出（Multiple睮nput Multiple睴utput,MIMO）架构，研究利用不完备信道状态信息（Channel State Information,CSI）下实现无线接入点（Access Point，AP）与用户（User Equipment，UE）之间的选择，提出基于深度强化学习（Deep Reinforcement Learning，DRL）的高效分配算法,通过使用不完备CSI快速生成以用户为中心的AP集合，减少了对前馈链路容量的占用。仿真结果表明，与其他传统选择算法相比，所提出的DRL接入点选择算法可以获得至少22.48%的总遍历频谱效率增益；与深度Q网络 (Deep睶睳etwork，DQN)算法相比，可以获得约14.17%的总频谱效率增益。 |
| 关键词: MIMO 以用户为中心的无蜂窝网络 接入点选择 深度强化学习 频谱效率增益 |
| DOI：10.20079/j.issn.1001-893x.230418003 |
|
| 基金项目:国家自然科学基金资助项目（61871239） |
|
| An Access Point Selection Algorithm for Cell-ree Systems Based on Deep Reinforcement Learning |
| ZHAO Wannan,SONG Xiaoyang,ZHAO Yingxin,WU Hong,LIU Zhiyang |
| (College of Electronic Information and Optical Engineering,Nankai University,Tianjin 300350,China) |
| Abstract: |
| The selection problem between wireless access point (AP) and user equipment (UE) in a user-entric cell-ree distributed multiple-nput multiple-utput (MIMO) system is investigated when only partial channel state information (CSI) is available.Based on deep reinforcement learning (DRL),an efficient AP selection algorithm is proposed,which uses partial CSI to rapidly generate a user-entric set of APs to reduce the occupancy of the fronthaul link.Simulation results demonstrate that the proposed DRL-ased AP selection algorithm can achieve sum ergodic spectrum efficiency gain of at least 22.48 |
| Key words: MIMO user-entric cell-ree network AP selection deep reinforcement learning spectral efficiency gain |
