Exploiting Deep Learning in Limited-Fronthaul Cell-Free Massive MIMO Uplink
Exploiting Deep Learning in Limited-Fronthaul Cell-Free Massive MIMO Uplink
复制标题
DOI：
10.1109/jsac.2020.3000812
复制
发表时间：
2020-02
影响因子：
16.4
通讯作者：
M. Bashar;A. Akbari;K. Cumanan;H. Ngo;A. Burr;P. Xiao;M. Debbah;J. Kittler
中科院分区：
文献类型：
--
作者：
M. Bashar;A. Akbari;K. Cumanan;H. Ngo;A. Burr;P. Xiao;M. Debbah;J. Kittler
考虑无小区大规模多输入多输出(MIMO)上行链路，其中量化转发(QF)指的是在接入点(AP)对信道估计和接收信号两者进行量化并将其转发到中央处理单元(CPU)的情况，而在组合量化转发(CQF)中，AP将组合信号的量化版本发送到CPU。为了解决非凸和速率最大化问题，采用一种启发式次优方案将功率分配问题转化为标准的几何规划问题。我们利用信道统计的知识来设计功率元件。将大尺度衰落(LSF)与深度卷积神经网络(DCNN)相结合，通过利用量化信道解决和速率最大化问题，使我们能够从LSF系数确定映射和最优功率。研究了四种可能的功率控制方案，我们称之为i)基于小规模衰落(SSF)的QF；ii)基于LSF的CQF；iii)基于LSF使用然后遗忘(UatF)的QF；以及iv)基于LSF深度学习(DL)的QF，根据在何处执行和利用信道估计以及如何解决优化问题。数值结果表明，在相同的波前率下，利用DCNN得到的映射可以显著提高吞吐量。
A cell-free massive multiple-input multiple-output (MIMO) uplink is considered, where quantize-and-forward (QF) refers to the case where both the channel estimates and the received signals are quantized at the access points (APs) and forwarded to a central processing unit (CPU) whereas in combine-quantize-and-forward (CQF), the APs send the quantized version of the combined signal to the CPU. To solve the non-convex sum rate maximization problem, a heuristic sub-optimal scheme is exploited to convert the power allocation problem into a standard geometric programme (GP). We exploit the knowledge of the channel statistics to design the power elements. Employing large-scale-fading (LSF) with a deep convolutional neural network (DCNN) enables us to determine a mapping from the LSF coefficients and the optimal power through solving the sum rate maximization problem using the quantized channel. Four possible power control schemes are studied, which we refer to as i) small-scale fading (SSF)-based QF; ii) LSF-based CQF; iii) LSF use-and-then-forget (UatF)-based QF; and iv) LSF deep learning (DL)-based QF, according to where channel estimation is performed and exploited and how the optimization problem is solved. Numerical results show that for the same fronthaul rate, the throughput significantly increases thanks to the mapping obtained using DCNN.