Doubly-selective channel estimation represents a key element in ensuring communication reliability in wireless systems. Due to the impact of multi-path propagation and Doppler interference in dynamic environments, doubly-selective channel estimation becomes challenging. Conventional channel estimation schemes encounter performance degradation in high mobility scenarios due to the usage of limited training pilots. Recently, deep learning (DL) has been utilized for doubly-selective channel estimation, where convolutional neural network (CNN) networks are employed in the frame-by-frame (FBF) channel estimation. However, CNN-based estimators require high complexity, making them impractical in real-case scenarios. For this purpose, we overcome this issue by proposing an optimized and robust bi-directional recurrent neural network (Bi-RNN) based channel estimator to accurately estimate the doubly-selective channel, especially in high mobility scenarios. The proposed estimator is based on performing end-to-end interpolation using gated recurrent unit (GRU) unit. Extensive numerical experiments demonstrate that the developed Bi-GRU estimator significantly outperforms the recently proposed CNN-based estimators in different mobility scenarios, while substantially reducing the overall computational complexity.

翻译：双选择性信道估计是确保无线系统通信可靠性的关键要素。由于动态环境中多径传播和多普勒干扰的影响，双选择性信道估计变得具有挑战性。传统信道估计方案因使用有限的训练导频，在高移动场景下性能会下降。近年来，深度学习已被用于双选择性信道估计，其中采用卷积神经网络进行逐帧信道估计。然而，基于CNN的估计器需要高复杂度，使其在实际场景中不实用。为此，我们通过提出一种优化且鲁棒的基于双向循环神经网络的信道估计器来克服这一问题，以准确估计双选择性信道，特别是在高移动场景下。所提出的估计器基于使用门控循环单元进行端到端插值。大量数值实验表明，所开发的Bi-GRU估计器在不同移动场景下显著优于近期提出的基于CNN的估计器，同时大幅降低了整体计算复杂度。