DEEP LEARNING AT THE EDGE FOR CHANNEL ESTIMATION IN BEYOND-5G MASSIVE MIMO
DEEP LEARNING AT THE EDGE FOR CHANNEL ESTIMATION IN BEYOND-5G MASSIVE MIMO
复制标题
DOI：
10.1109/mwc.001.2000322
复制
发表时间：
2021-04-01
影响因子：
12.9
通讯作者：
Chowdhury, Kaushik R.
中科院分区：
文献类型：
--
作者：
Belgiovine, Mauro;Sankhe, Kunal;Chowdhury, Kaushik R.
大规模多输入多输出（mMIMO）是即将到来的5G无线部署中的关键组件，作为高数据速率通信的推动者。当各个发射机-接收机阵列的每个对应天线对经历独立信道时，mMIMO是有效的。虽然增加天线元件的数量增加了可实现的数据速率，但同时计算信道状态信息（CSI）变得过于昂贵。在本文中，我们建议通过多层感知器架构使用深度学习，该架构超过了传统CSI处理方法（如最小二乘（LS）和线性最小均方误差（LMMSE）估计）的性能，从而导致超越第五代（B5 G）网络范式，其中机器学习完全驱动网络优化。通过我们的深度学习方法同时计算所有成对信道的CSI，与传统的估计方法相比，我们的方法可以扩展到大型天线阵列。这里的关键见解是设计学习架构，使其可在大规模并行架构（如GPU或FPGA）上实现。我们验证我们的方法，通过模拟一个32元阵列基站和一个用户设备与4元阵列工作在毫米波频段。结果表明，最快的LS估计和最佳LMMSE，分别在BER的五个和两个数量级的改善，大大提高了端到端的系统性能，并提供更高的空间分集为较低的SNR区域，实现高达4 dB的增益接收功率信号相比，通过LMMSE估计获得的性能。
Massive multiple-input multiple-output (mMIMO) is a critical component in upcoming 5G wireless deployment as an enabler for high data rate communications. mMIMO is effective when each corresponding antenna pair of the respective transmitter-receiver arrays experiences an independent channel. While increasing the number of antenna elements increases the achievable data rate, at the same time computing the channel state information (CSI) becomes prohibitively expensive. In this article, we propose to use deep learning via a multi-layer perceptron architecture that exceeds the performance of traditional CSI processing methods like least square (LS) and linear minimum mean square error (LMMSE) estimation, thus leading to a beyond fifth generation (B5G) networking paradigm wherein machine learning fully drives networking optimization. By computing the CSI of all pairwise channels simultaneously via our deep learning approach, our method scales with large antenna arrays as opposed to traditional estimation methods. The key insight here is to design the learning architecture such that it is implementable on massively parallel architectures, such as GPU or FPGA. We validate our approach by simulating a 32-element array base station and a user equipment with a 4-element array operating on millimeter-wave frequency band. Results reveal an improvement up to five and two orders of magnitude in BER with respect to fastest LS estimation and optimal LMMSE, respectively, substantially improving the end-to-end system performance and providing higher spatial diversity for lower SNR regions, achieving up to 4 dB gain in received power signal compared to performance obtained through LMMSE estimation.