Research on machine learning for channel estimation, especially neural network solutions for wireless communications, is attracting significant current interest. This is because conventional methods cannot meet the present demands of the high speed communication. In the paper, we deploy a general residual convolutional neural network to achieve channel estimation for the orthogonal frequency-division multiplexing (OFDM) signals in a downlink scenario. Our method also deploys a simple interpolation layer to replace the transposed convolutional layer used in other networks to reduce the computation cost. The proposed method is more easily adapted to different pilot patterns and packet sizes. Compared with other deep learning methods for channel estimation, our results for 3GPP channel models suggest improved mean squared error performance for our approach.
翻译:用于频道估算的机器学习研究,特别是无线通信神经网络解决方案,正在引起重大的兴趣。这是因为常规方法无法满足目前高速通信的需求。在论文中,我们部署了一个一般的剩余神经神经网络,以在下行链路情景中实现对正方位频率变化多路信号的频道估计。我们的方法还部署一个简单的内插层,以取代其他网络中用于降低计算成本的变换电流层。拟议方法更容易适应不同的试点模式和包体大小。与其他深入的频道估算学习方法相比,我们3GPP频道模型的结果显示,我们方法的平方差差差率表现有所改善。