Novel Deep Neural OFDM Receiver Architectures for LLR Estimation
This work addresses the challenge of enhancing signal decoding in communication systems for applications like wireless networks, though it appears incremental as it builds on existing neural receiver approaches.
The authors tackled the problem of improving OFDM receiver performance by proposing two novel neural network architectures, DAT and RDNLA, for channel estimation and equalization to predict LLRs from IQ signals, resulting in better BER and BLER performance compared to traditional systems and existing neural models across various SNR levels.
Neural receivers have recently become a popular topic, where the received signals can be directly decoded by data driven mechanisms such as machine learning and deep learning. In this paper, we propose two novel neural network based orthogonal frequency division multiplexing (OFDM) receivers performing channel estimation and equalization tasks and directly predicting log likelihood ratios (LLRs) from the received in phase and quadrature phase (IQ) signals. The first network, the Dual Attention Transformer (DAT), employs a state of the art (SOTA) transformer architecture with an attention mechanism. The second network, the Residual Dual Non Local Attention Network (RDNLA), utilizes a parallel residual architecture with a non local attention block. The bit error rate (BER) and block error rate (BLER) performance of various SOTA neural receiver architectures is compared with our proposed methods across different signal to noise ratio (SNR) levels. The simulation results show that DAT and RDNLA outperform both traditional communication systems and existing neural receiver models.