Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback

Abstract

In multiple-input multiple-output (MIMO) systems, it is crucial of utilizing the available channel state information (CSI) at the transmitter for precoding to improve the performance of frequency division duplex (FDD) networks. One of the mainchallenges is to compress a large amount of CSI in CSI feedback transmission in massive MIMO systems. In this paper, we propose a deep learning (DL)-based approach that uses a deep recurrent neural network (RNN) to learn temporal correlation and adopts depthwise separable convolution to shrink the model. The feature extraction module is also elaborately devised by studyingdecoupled spatio-temporal feature representations in different structures. Experimental results demonstrate that the proposed approach outperforms existing DL-based methods in terms of recovery quality and accuracy, which can also achieve remarkable robustness at low compression ratio (CR).

arXiv comment5pages, 6figures, 14conference

References in corpus (5)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Over the Air Deep Learning Based Radio Signal Classification
• Downlink Training Techniques for FDD Massive MIMO Systems: Open-Loop and Closed-Loop Training with Memory
• On Capacity of Large-Scale MIMO Multiple Access Channels with Distributed Sets of Correlated Antennas
• Deep Learning Based MIMO Communications

Cited by in corpus (6)

• Deep Learning-based Implicit CSI Feedback in Massive MIMO
• Deep Learning for Joint Channel Estimation and Feedback in Massive MIMO Systems
• Recursive CSI Quantization of Time-Correlated MIMO Channels by Deep Learning Classification
• Deep Learning for 1-Bit Compressed Sensing-based Superimposed CSI Feedback
• Deep Learning-Based CSI Feedback for Beamforming in Single- and Multi-cell Massive MIMO Systems
• ELM-based Superimposed CSI Feedback for FDD Massive MIMO System