School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, China.
PLoS One. 2022 May 27;17(5):e0268952. doi: 10.1371/journal.pone.0268952. eCollection 2022.
Data-nulling superimposed pilot (DNSP) effectively alleviates the superimposed interference of superimposed training (ST)-based channel estimation (CE) in orthogonal frequency division multiplexing (OFDM) systems, while facing the challenges of the estimation accuracy and computational complexity. By developing the promising solutions of deep learning (DL) in the physical layer of wireless communication, we fuse the DNSP and DL to tackle these challenges in this paper. Nevertheless, due to the changes of wireless scenarios, the model mismatch of DL leads to the performance degradation of CE, and thus faces the issue of network retraining. To address this issue, a lightweight transfer learning (TL) network is further proposed for the DL-based DNSP scheme, and thus structures a TL-based CE in OFDM systems. Specifically, based on the linear receiver, the least squares estimation is first employed to extract the initial features of CE. With the extracted features, we develop a convolutional neural network (CNN) to fuse the solutions of DL-based CE and the CE of DNSP. Finally, a lightweight TL network is constructed to address the model mismatch. To this end, a novel CE network for the DNSP scheme in OFDM systems is structured, which improves its estimation accuracy and alleviates the model mismatch. The experimental results show that in all signal-to-noise-ratio (SNR) regions, the proposed method achieves lower normalized mean squared error (NMSE) than the existing DNSP schemes with minimum mean square error (MMSE)-based CE. For example, when the SNR is 0 decibel (dB), the proposed scheme achieves similar NMSE as that of the MMSE-based CE scheme at 20 dB, thereby significantly improving the estimation accuracy of CE. In addition, relative to the existing schemes, the improvement of the proposed scheme presents its robustness against the impacts of parameter variations.
数据置零叠加导频（DNSP）有效缓解了基于叠加训练（ST）的信道估计（CE）在正交频分复用（OFDM）系统中的叠加干扰，同时面临着估计精度和计算复杂度的挑战。通过在无线通信物理层开发有前途的深度学习（DL）解决方案，我们将 DNSP 和 DL 融合在一起，以解决本文中的这些挑战。然而，由于无线场景的变化，DL 的模型失配导致 CE 的性能下降，因此面临网络重新训练的问题。为了解决这个问题，进一步提出了一种轻量级的迁移学习（TL）网络，用于基于 DL 的 DNSP 方案，从而在 OFDM 系统中构建了基于 TL 的 CE。具体来说，基于线性接收机，首先采用最小二乘估计来提取 CE 的初始特征。利用提取的特征，我们开发了一个卷积神经网络（CNN）来融合基于 DL 的 CE 和 DNSP 的 CE 的解决方案。最后，构建了一个轻量级的 TL 网络来解决模型失配问题。为此，构建了一种新颖的 OFDM 系统中 DNSP 方案的 CE 网络，提高了其估计精度并缓解了模型失配问题。实验结果表明，在所有信噪比（SNR）区域中，所提出的方法都比具有最小均方误差（MMSE）的基于 CE 的现有 DNSP 方案具有更低的归一化均方误差（NMSE）。例如，当 SNR 为 0 分贝（dB）时，与 MMSE 基于 CE 的方案相比，所提出的方案在 20 dB 时具有相似的 NMSE，从而显著提高了 CE 的估计精度。此外，与现有方案相比，所提出方案的改进方案表现出对参数变化影响的鲁棒性。
