Deep Learning for Massive MIMO CSI Feedback-学习笔记

jinshi，chao-kai wen

Abstract

In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited.

在频分双工模式下，下行链路信道状态信息（CSI）应通过反馈链路发送到基站，以便能够显示大规模多输入多输出的潜在增益。

However, such a transmission is hindered by excessive feedback overhead. In this letter, we use deep learning technology to develop CsiNet, a novel CSI sensing and recovery mechanism that learns to effectively use channel structure from training samples. 然而，这样的传输受到过多反馈开销的阻碍。在这封信中，我们使用深度学习技术来开发CsiNet，这是一种新的CSI感知和恢复机制，它学习如何从训练样本中有效地使用信道结构。

CsiNet learns a trans-formation from CSI to a near-optimal number of representations (or codewords) and an inverse transformation from codewords to CSI. We perform experiments to demonstrate that CsiNet can
recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based meth-ods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.

CsiNet学习从CSI到接近最佳数量的表示（或码字）的转换，以及从码字到CSI的逆变换。我们通过实验证明，与现有的基于压缩感知（CS）的方法相比，CsiNet可以在显著提高重建质量的情况下恢复CSI。即使在基于CS的方法无法工作的极低压缩区域，CsiNet仍能保持有效的波束形成增益。

I. INTRODUCTION

MIMO系统系统可以显著减少多用户干扰并提供多倍的小区吞吐量增长。这种潜在的好处主要是通过利用BSs处的信道状态信息（CSI）获得的。

the downlink CSI is acquired at the user equipment (UE) dur-ing the training period and returns to the BS through feedback links. Vector quantization or codebook-based approaches are usually adopted to reduce feedback overhead. However, the feedback quantities resulting from these approaches need to be scaled linearly with the number of transmit antennas and are prohibitive in a massive MIMO regime.

在训练期间在用户设备（UE）处获取下行链路CSI，并通过反馈链路返回BS。通常采用矢量量化或基于码本的方法来减少反馈开销。然而，这些方法产生的反馈量需要与发射天线的数量成线性比例，并且在大规模MIMO体制中是禁止的

[3], [4]. These works have
mainly focused on reducing feedback overhead by using the spatial and temporal correlation of CSI. （CSI的空间和时间相关性）[3] P .-H. Kuo, H. T. Kung, and P .-A. Ting, “Compressive sensing based channel feedback protocols for spatially-correlated massive antenna arrays,” inProc. IEEE WCNC, Shanghai, China, Apr. 2012, pp. 492–497.[4] X. Rao and V . K. N. Lau, “Distributed compressive CSIT estimation and feedback for FDD multi-user massive MIMO systems,”IEEE Trans. Signal Process., vol. 62, no. 12, pp. 3261–3271, Jun. 2014.

In particular, correlated CSI can be transformed into an uncorrelated sparse vector in some bases; thus, one can use compressive sensing (CS) to obtain a sufficiently accurate estimate of a sparse vector from an underdetermined linear system. 特别地，相关CSI可以在一些基中转换成不相关的稀疏向量；因此，可以使用压缩感知（CS）从欠定线性系统获得稀疏向量的足够精确的估计。

The use of several algorithms, including LASSO?1-solver [5] and AMP [6], has also been proposed in CS. However, these algorithms [5], [6] struggle to recover