Attention-Aided MMSE for OFDM Channel Estimation: Learning Linear Filters with Attention
This work addresses channel estimation for OFDM systems, offering a more efficient solution for practical wireless communication applications, though it appears incremental as it builds on existing model-based DNN and attention methods.
The paper tackles the problem of high inference complexity in deep neural network-based channel estimation for OFDM by proposing an Attention-aided MMSE (A-MMSE) framework, which learns the optimal MMSE filter via a Transformer and reduces computational complexity through a single linear operation during inference, achieving improved normalized MSE across various SNR conditions in simulations with 3GPP TDL models.
In orthogonal frequency division multiplexing (OFDM), accurate channel estimation is crucial. Classical signal processing based approaches, such as minimum mean-squared error (MMSE) estimation, often require second-order statistics that are difficult to obtain in practice. Recent deep neural networks based methods have been introduced to address this; yet they often suffer from high inference complexity. This paper proposes an Attention-aided MMSE (A-MMSE), a novel model-based DNN framework that learns the optimal MMSE filter via the Attention Transformer. Once trained, the A-MMSE estimates the channel through a single linear operation for channel estimation, eliminating nonlinear activations during inference and thus reducing computational complexity. To enhance the learning efficiency of the A-MMSE, we develop a two-stage Attention encoder, designed to effectively capture the channel correlation structure. Additionally, a rank-adaptive extension of the proposed A-MMSE allows flexible trade-offs between complexity and channel estimation accuracy. Extensive simulations with 3GPP TDL channel models demonstrate that the proposed A-MMSE consistently outperforms other baseline methods in terms of normalized MSE across a wide range of signal-to-noise ratio (SNR) conditions. In particular, the A-MMSE and its rank-adaptive extension establish a new frontier in the performance-complexity trade-off, providing a powerful yet highly efficient solution for practical channel estimation