In order to unlock the full advantages of massive multiple input multiple output (MIMO) in the downlink, channel state information (CSI) is required at the base station (BS) to optimize the beamforming matrices. In frequency division duplex (FDD) systems, full channel reciprocity does not hold, and CSI acquisition generally requires downlink pilot transmission followed by uplink feedback. Prior work proposed the end-to-end design of pilot transmission, feedback, and CSI estimation via deep learning. In this work, we introduce an enhanced end-to-end design that leverages partial uplink-downlink reciprocity and temporal correlation of the fading processes by utilizing jointly downlink and uplink pilots. The proposed method is based on a novel deep learning architecture -- HyperRNN -- that combines hypernetworks and recurrent neural networks (RNNs) to optimize the transfer of long-term channel features from uplink to downlink. Simulation results demonstrate that the HyperRNN achieves a lower normalized mean square error (NMSE) performance, and that it reduces requirements in terms of pilot lengths.
翻译:为了在下行链路中解开大量多输入多重输出(MIIMO)的全部优势,基地台需要频道状态信息(CSI)来优化光成矩阵。在频谱分区双面(DFD)系统中,全频道对等不起作用,而CSI的获取通常需要下行链路试点传输,然后提供上行链路反馈。先前的工作提议通过深层次学习来设计试点传输、反馈和CSI估算的端到端设计。在这项工作中,我们引入了一个强化端到端设计,利用联合下行链路和上端链路试点项目来利用淡化过程的部分上链-下行链路对等和时间相关性。拟议的方法基于一个新的深层次的学习结构 -- -- 超网络和经常性神经网络(RNNN),以优化从上行链路至下行链路连接的长期频道特征的转移。模拟结果显示超端网将达到较低的正常中位平方差性能,并降低试点长度的要求。