When base stations (BSs) are deployed with multiple antennas, they need to have downlink (DL) channel state information (CSI) to optimize downlink transmissions by beamforming. The DL CSI is usually measured at mobile stations (MSs) through DL training and fed back to the BS in frequency division duplexing (FDD). The DL training and uplink (UL) feedback might become infeasible due to insufficient coherence time interval when the channel rapidly changes due to high speed of MSs. Without the feedback from MSs, it may be possible for the BS to directly obtain the DL CSI using the inherent relation of UL and DL channels even in FDD, which is called DL extrapolation. Although the exact relation would be highly nonlinear, previous studies have shown that a neural network (NN) can be used to estimate the DL CSI from the UL CSI at the BS. Most of previous works on this line of research trained the NN using full dimensional UL and DL channels; however, the NN training complexity becomes severe as the number of antennas at the BS increases. To reduce the training complexity and improve DL CSI estimation quality, this paper proposes a novel DL extrapolation technique using simplified input and output of the NN. It is shown through many measurement campaigns that the UL and DL channels still share common components like path delays and angles in FDD. The proposed technique first extracts these common coefficients from the UL and DL channels and trains the NN only using the path gains, which depend on frequency bands, with reduced dimension compared to the full UL and DL channels. Extensive simulation results show that the proposed technique outperforms the conventional approach, which relies on the full UL and DL channels to train the NN, regardless of the speed of MSs.

中文翻译：

---

使用提取的上行链路增益通过神经网络对 FDD 多天线系统进行下行链路外推

当基站 (BS) 部署有多个天线时，它们需要具有下行链路 (DL) 信道状态信息 (CSI) 以通过波束成形优化下行链路传输。DL CSI 通常在移动台 (MS) 处通过 DL 训练进行测量，并在频分双工 (FDD) 中反馈给 BS。当信道由于 MS 高速变化而快速变化时，DL 训练和上行链路 (UL) 反馈可能会由于相干时间间隔不足而变得不可行。在没有来自 MS 的反馈的情况下，即使在 FDD 中，BS 也可以使用 UL 和 DL 信道的固有关系直接获得 DL CSI，这称为 DL 外推。尽管确切的关系是高度非线性的，但先前的研究表明，神经网络 (NN) 可用于从 BS 处的 UL CSI 估计 DL CSI。这方面的大部分先前工作都使用全维 UL 和 DL 通道训练神经网络；然而，随着 BS 天线数量的增加，NN 训练的复杂性变得很严重。为了降低训练复杂度并提高 DL CSI 估计质量，本文提出了一种使用简化的 NN 输入和输出的新型 DL 外推技术。许多测量活动表明，UL 和 DL 信道仍然共享通用组件，如 FDD 中的路径延迟和角度。所提出的技术首先从 UL 和 DL 信道中提取这些公共系数，并仅使用依赖于频带的路径增益来训练 NN，与完整的 UL 和 DL 信道相比，具有减少的维度。广泛的仿真结果表明，所提出的技术优于传统方法，