Joint User and Data Detection in Grant-Free NOMA with Attention-based BiLSTM Network

TL;DR

This work addresses AUD and MUD in uplink grant-free NOMA under burst sparsity by proposing an attention-based BiLSTM network that exploits temporal correlations without requiring prior sparsity or channel knowledge. The model maps the stacked received signals to the active device support, and uses that estimate for blind data detection via MMSE weighting with known spreading sequences. Results show substantial improvements over traditional CS-based methods and ML baselines in detection, device identification, and BER, with favorable computational complexity and strong generalization to varying system parameters. The approach offers a practical, scalable solution for fast access in massive IoT deployments using complex spreading signatures.

Abstract

We consider the multi-user detection (MUD) problem in uplink grant-free non-orthogonal multiple access (NOMA), where the access point has to identify the total number and correct identity of the active Internet of Things (IoT) devices and decode their transmitted data. We assume that IoT devices use complex spreading sequences and transmit information in a random-access manner following the burst-sparsity model, where some IoT devices transmit their data in multiple adjacent time slots with a high probability, while others transmit only once during a frame. Exploiting the temporal correlation, we propose an attention-based bidirectional long short-term memory (BiLSTM) network to solve the MUD problem. The BiLSTM network creates a pattern of the device activation history using forward and reverse pass LSTMs, whereas the attention mechanism provides essential context to the device activation points. By doing so, a hierarchical pathway is followed for detecting active devices in a grant-free scenario. Then, by utilising the complex spreading sequences, blind data detection for the estimated active devices is performed. The proposed framework does not require prior knowledge of device sparsity levels and channels for performing MUD. The results show that the proposed network achieves better performance compared to existing benchmark schemes.

Figures (9)

• Figure 1: Illustration of a typical uplink grant-free NOMA system.
• Figure 2: Detailed architecture and working of the proposed attention-based BiLSTM network.
• Figure 3: The proposed BiLSTM module with an attention mechanism.
• Figure 4: Validation loss $\mathcal{J}_v(\Theta)$ for different number of hidden layers $L$, with total number of devices $K = 200$, number of subcarriers $N = 100$, and number of active devices $S = 20$.
• Figure 5: Probability of detection, $\rho_d$, versus SNR (dB) for the number of active devices $S$, with the total number of potential devices $K = 200$, and the number of subcarriers $N = 100$.