Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels

By Tianqi Wang, Chao-Kai Wen, Shi Jin, Geoffrey Y. Li. IEEE Wireless Communications Letters, 2018

411 citations recorded by the source corpus.

Massive multiple-input multiple-output (MIMO) systems rely on channel state information (CSI) feedback to perform precoding and achieve performance gain in frequency division duplex networks. However, the huge number of antennas poses a challenge to the conventional CSI feedback reduction methods and leads to excessive feedback overhead. In this letter, we develop a real-time CSI feedback architecture, called CsiNet-long short-term memory (LSTM), by extending a novel deep learning (DL)-based CSI sensing and recovery network. CsiNet-LSTM considerably enhances recovery quality and improves tradeoff between compression ratio (CR) and complexity by directly learning spatial structures combined with time correlation from training samples of time-varying massive MIMO channels. Simulation results demonstrate that CsiNet-LSTM outperforms existing compressive sensing-based and DL-based methods and is remarkably robust to CR reduction.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/2a920d6f16348e19fa29e52c39ae7be4b4e5fd14

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis (2019, methodology): “Then, CsiNet-LSTM in [23] improves the reconstruction accuracy by considering the temporal correlations of CSI utilizing long-short time memory (LSTM) architecture [24].”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, background): “Furthermore, [28] proposed a real-time CSI feedback architecture called CsiNet-long short-term memory for time-varying massive multiple-inputmultiple-output (MIMO) channels.”
Machine Learning in the Air (2019, methodology): “architecture in [54], where a more advanced autoencoder architecture is employed compared to [49], and trained together”
Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems (2019, methodology): “introduced in [18] to develop a more efficient channel compression and recovery method for the CSI feedback.”