Deep-Unfolded Joint Activity and Data Detection for Grant-Free Transmission in Cell-Free Systems

TL;DR

The paper tackles joint activity and data detection for massive grant-free transmissions in cell-free networks by introducing DU-JAD, a deep-unfolded extension of a box-constrained forward-backward splitting solver. By unfolding multiple FBS iterations into trainable modules and incorporating a momentum-enabled forward step, an approximate posterior mean estimator for data, and a soft-output AUD component, the approach achieves improved user activity detection and data detection with reduced iteration counts. A dedicated training scheme optimizes both FBS parameters and the AUD module, yielding robust performance in simulations with hundreds of users and many access points. The results demonstrate significant gains over baselines in both AUD and DD metrics, highlighting the practical impact for low-latency, scalable cell-free mMTC systems.

Abstract

Massive grant-free transmission and cell-free wireless communication systems have emerged as pivotal enablers for massive machine-type communication. This paper proposes a deep-unfolding-based joint activity and data detection (DU-JAD) algorithm for massive grant-free transmission in cell-free systems. We first formulate a joint activity and data detection optimization problem, which we solve approximately using forward-backward splitting (FBS). We then apply deep unfolding to FBS to optimize algorithm parameters using machine learning. In order to improve data detection (DD) performance, reduce algorithm complexity, and enhance active user detection (AUD), we employ a momentum strategy, an approximate posterior mean estimator, and a novel soft-output AUD module, respectively. Simulation results confirm the efficacy of DU-JAD for AUD and DD.

Figures (3)

• Figure 1: Architecture of the DU-JAD algorithm.
• Figure 2: Active user detection performance.
• Figure 3: Data detection performance.