Channel estimation is of crucial importance in massive multiple-input multiple-output (m-MIMO) visible light communication (VLC) systems. In order to tackle this problem, a fast and flexible denoising convolutional neural network (FFDNet)-based channel estimation scheme for m-MIMO VLC systems was proposed. The channel matrix of the m-MIMO VLC channel is identified as a two-dimensional natural image since the channel has the characteristic of sparsity. A deep learning-enabled image denoising network FFDNet is exploited to learn from a large number of training data and to estimate the m-MIMO VLC channel. Simulation results demonstrate that our proposed channel estimation based on the FFDNet significantly outperforms the benchmark scheme based on minimum mean square error.

中文翻译：

---

用于大规模 MIMO 可见光通信系统的基于 FFDNet 的信道估计

信道估计在大规模多输入多输出 (m-MIMO) 可见光通信 (VLC) 系统中至关重要。为了解决这个问题，提出了一种快速灵活的基于卷积神经网络（FFDNet）去噪的 m-MIMO VLC 系统信道估计方案。由于信道具有稀疏性，因此m-MIMO VLC信道的信道矩阵被识别为二​​维自然图像。启用深度学习的图像去噪网络 FFDNet 用于从大量训练数据中学习并估计 m-MIMO VLC 信道。仿真结果表明，我们提出的基于 FFDNet 的信道估计明显优于基于最小均方误差的基准方案。