AdaFortiTran: An Adaptive Transformer Model for Robust OFDM Channel Estimation

TL;DR

AdaFortiTran is an innovative transformer-based model that significantly improves OFDM channel estimation accuracy and robustness in fast-fading and low-SNR conditions by combining local and global feature extraction with adaptive priors.

Contribution

The paper introduces AdaFortiTran, a novel adaptive transformer architecture that integrates convolutional layers, attention mechanisms, and prior information to enhance OFDM channel estimation in challenging environments.

Findings

Achieves up to 6 dB reduction in MSE compared to state-of-the-art models.

Demonstrates robustness across high Doppler shifts and low SNR scenarios.

Effectively models both local correlations and long-range dependencies in OFDM channels.

Abstract

Deep learning models for channel estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems often suffer from performance degradation under fast-fading channels and low-SNR scenarios. To address these limitations, we introduce the Adaptive Fortified Transformer (AdaFortiTran), a novel model specifically designed to enhance channel estimation in challenging environments. Our approach employs convolutional layers that exploit locality bias to capture strong correlations between neighboring channel elements, combined with a transformer encoder that applies the global Attention mechanism to channel patches. This approach effectively models both long-range dependencies and spectro-temporal interactions within single OFDM frames. We further augment the model's adaptability by integrating nonlinear representations of available channel statistics SNR, delay spread, and Doppler shift as priors. A residual connection is employed to merge global features from the transformer with local features from early convolutional processing, followed by final convolutional layers to refine the hierarchical channel representation. Despite its compact architecture, AdaFortiTran achieves up to 6 dB reduction in mean squared error (MSE) compared to state-of-the-art models. Tested across a wide range of Doppler shifts (200-1000 Hz), SNRs (0 to 25 dB), and delay spreads (50-300 ns), it demonstrates superior robustness in high-mobility environments.