Lightweight Differential Frameworks for CSI Feedback in Time-Varying Massive MIMO Systems

Channel state information (CSI) is vital for massive multiple-input multiple-output (MIMO) systems to provide high channel capacity and energy efficiency. However, the massive antennas will lead to high feedback overhead in frequency division duplex (FDD) MIMO systems. To leverage the temporal correlation of the channel in CSI feedback, recent applications of recurrent neural networks have demonstrated promising results but with tremendous complexity. The MarkovNet reduces the overall complexity but owns the high complexity at the user equipment (UE), which is not suitable for practical deployment. In this work, we aim to improve the reconstruction performance and reduce the complexity of the UE. Leveraging the channel temporal correlation, we propose two differential frameworks called DIFNet1 and DIFNet2 to improve feedback accuracy and efficiency. Moreover, we explore the real part and imaginary part correlations of channel differential terms to reduce the complexity. Finally, we unfold the Iterative Shrinkage-Thresholding Algorithm (ISTA) to provide excellent reconstruction performance. Simulation results demonstrate that the proposed frameworks improve the reconstruction performance while greatly reducing the complexity of UEs.