Deep Unfolding Enabled Sparse Signal Recovery in Cell-Free IoT System

Massive devices co-exist in IoT systems and the connection is sparse due to burst IoT service. To address this issue, in this paper we propose a deep unfolding network based on the alternating direction method of multipliers (ADMM) algorithm to compress and recover signals in a cell-free IoT system with massive connectivity. Redundancy analysis operator is learned to complete the compress sensing (CS) work. In addition, we compare our proposed network with the iterative shrinkage thresholding algorithm (ISTA) that also learns orthogonal sparsifier with the ADMM network. Finally, simulation experiments demonstrate that our proposed scheme shows better performance.