Unsupervised Learning Based Fast Beamforming Design for Downlink MIMO
Unsupervised Learning Based Fast Beamforming Design for Downlink MIMO
复制标题
基于无监督学习的下行 MIMO 快速波束成形设计
DOI：
10.1109/access.2018.2887308
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
XIAOMEI ZHU
中科院分区：
文献类型：
--
作者：
HAO HUANG;WENCHAO XIA;JIAN XIONG;JIE YANG;GAN ZHENG;XIAOMEI ZHU
在下行传输场景中，当使用多天线阵列时，发射机的功率分配和波束形成设计是必不可少的。考虑在总功率约束下的多输入多输出广播信道加权和速率最大化问题。经典加权最小均方误差（WMMSE）算法可以得到次优解，但计算量大。为了降低这种复杂性，我们提出了一种使用无监督学习的快速波束形成设计方法，该方法离线训练深度神经网络（DNN），仅通过简单的神经网络操作在线提供实时服务。训练过程基于端到端方法，无需标记样本，避免了获取标签的复杂过程。此外，我们使用基于“APoZ”的剪枝算法来压缩网络体积，这进一步降低了DNN的计算复杂度和体积，使其更适合于低计算能力的设备。最后，实验结果表明，该方法显著提高了计算速度，性能接近WMMSE算法。
In the downlink transmission scenario, power allocation and beamforming design at the transmitter are essential when using multiple antenna arrays. This paper considers a multiple input–multiple output broadcast channel to maximize the weighted sum-rate under the total power constraint. The classical weighted minimum mean-square error (WMMSE) algorithm can obtain suboptimal solutions but involves high computational complexity. To reduce this complexity, we propose a fast beamforming design method using unsupervised learning, which trains the deep neural network (DNN) offline and provides real-time service online only with simple neural network operations. The training process is based on an end-to-end method without labeled samples avoiding the complicated process of obtaining labels. Moreover, we use the “APoZ”-based pruning algorithm to compress the network volume, which further reduces the computational complexity and volume of the DNN, making it more suitable for low computation-capacity devices. Finally, the experimental results demonstrate that the proposed method improves computational speed significantly with performance close to the WMMSE algorithm.