Deep Learning Phase Compression for MIMO CSI Feedback by Exploiting FDD Channel Reciprocity

Large scale MIMO FDD systems are often hampered by bandwidth required to feedback downlink CSI. Previous works have made notable progresses in efficient CSI encoding and recovery by taking advantage of FDD uplink/downlink reciprocity between their CSI magnitudes. Such framework separately encodes CSI phase and magnitude. To further enhance feedback efficiency, we propose a new deep learning architecture for phase encoding based on limited CSI feedback and magnitude-aided information. Our contribution features a framework with a modified loss function to enable end-to-end joint optimization of CSI magnitude and phase recovery. Our test results show superior performance in indoor/outdoor scenarios.

[1]  Lars Thiele,et al.  QuaDRiGa: A 3-D Multi-Cell Channel Model With Time Evolution for Enabling Virtual Field Trials , 2014, IEEE Transactions on Antennas and Propagation.

[2]  Geoffrey Ye Li,et al.  DL-based CSI Feedback and Cooperative Recovery in Massive MIMO , 2020, ArXiv.

[3]  Giambattista Parascandolo,et al.  Taming the waves: sine as activation function in deep neural networks , 2017 .

[4]  Shi Jin,et al.  Deep Learning for Massive MIMO CSI Feedback , 2017, IEEE Wireless Communications Letters.

[5]  Geoffrey Ye Li,et al.  Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis , 2019, IEEE Transactions on Wireless Communications.

[6]  Zhi Ding,et al.  Exploiting Bi-Directional Channel Reciprocity in Deep Learning for Low Rate Massive MIMO CSI Feedback , 2019, IEEE Wireless Communications Letters.

[7]  Zhi Ding,et al.  Learning-Based Phase Compression and Quantization for Massive MIMO CSI Feedback with Magnitude-Aided Information , 2021, ArXiv.

[8]  Zhi Ding,et al.  A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI Feedback , 2020, IEEE Transactions on Wireless Communications.

[9]  Claude Oestges,et al.  The COST 2100 MIMO channel model , 2011, IEEE Wirel. Commun..

[10]  Zhi Ding,et al.  An Efficient Deep Learning Framework for Low Rate Massive MIMO CSI Reporting , 2019, IEEE Transactions on Communications.

[11]  Biing-Hwang Juang,et al.  Deep Learning in Physical Layer Communications , 2018, IEEE Wireless Communications.