Deep Learning for Massive MIMO CSI Feedback

  title={Deep Learning for Massive MIMO CSI Feedback},
  author={Chao-Kai Wen and Wan-Ting Shih and Shi Jin},
  journal={IEEE Wireless Communications Letters},
In frequency division duplex mode, the downlink channel state information (CSI) should be sent to the base station through feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, such a transmission is hindered by excessive feedback overhead. In this letter, we use deep learning technology to develop CsiNet, a novel CSI sensing and recovery mechanism that learns to effectively use channel structure from training samples. CsiNet learns a… 
Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels
A real-time CSI feedback architecture, called CsiNet-long short-term memory (LSTM), is developed by extending a novel deep learning (DL)-based CSI sensing and recovery network that outperforms existing compressive sensing-based and DL-based methods and is remarkably robust to CR reduction.
Lightweight Convolutional Neural Networks for CSI Feedback in Massive MIMO
A DL-based CSI feedback network is developed in this study to complete the feedback of CSI effectively but this network cannot be effectively applied to the mobile terminal due to its excessive number of parameters and high computational complexity.
Deep Convolutional Compression For Massive MIMO CSI Feedback
A deep learning based channel state matrix compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks is proposed, which significantly outperforms the state of the art compression schemes in terms of the reconstruction quality of theChannel state matrix for the same compression rate.
Distributed Deep Convolutional Compression for Massive MIMO CSI Feedback
A deep learning (DL)-based CSI compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks, which outperforms the state of the art CSI compression schemes in terms of the reconstruction quality of CSI for the same compression rate.
A Novel Compression CSI Feedback based on Deep Learning for FDD Massive MIMO Systems
A deep learning-based modular adaptive multiple-rate (MAMR) compression CSI feedback framework that realizes a general autoencoder performing variable-rate compression.
A Novel Quantization Method for Deep Learning-Based Massive MIMO CSI Feedback
This paper proposes a novel quantization framework and training strategy for DL-based CSI feedback, which not only makes the current CSI feedback network applicable in real communication systems but also minimizes the introduced quantization distortion to improve the reconstruction quality.
Deep Learning-based Implicit CSI Feedback in Massive MIMO
A DL-based implicit feedback architecture to inherit the low-overhead characteristic is proposed, which uses neural networks (NNs) to replace the precoding matrix indicator (PMI) encoding and decoding modules and can achieve a more refined mapping between the precode matrix and the PMI compared with codebooks.
Deep Learning-Based Denoise Network for CSI Feedback in FDD Massive MIMO Systems
Numerical results show that the DL-based feedback algorithm with the proposed DNNet has superior performance over the existing algorithms, especially at low signal-to-noise ratio (SNR).
Exploiting Bi-Directional Channel Reciprocity in Deep Learning for Low Rate Massive MIMO CSI Feedback
Two deep learning architectures are proposed, Dual net-MAG and DualNet-ABS, to significantly reduce the CSI feedback payload based on the multipath reciprocity, based on limited feedback and bi-directional reciprocal channel characteristics.
An Efficient Deep Learning Framework for Low Rate Massive MIMO CSI Reporting
This work develops an efficient DL-based compression framework CQNet to jointly tackle CSI compression, codeword quantization, and recovery under the bandwidth constraint and proposes a more efficient quantization scheme in the radial coordinate by introducing a novel magnitude-adaptive phase quantization framework.


Distributed Compressive CSIT Estimation and Feedback for FDD Multi-User Massive MIMO Systems
  • Xiongbin Rao, V. Lau
  • Computer Science, Mathematics
    IEEE Transactions on Signal Processing
  • 2014
This paper considers multi-user massive MIMO systems and proposes a distributed compressive CSIT estimation scheme so that the compressed measurements are observed at the users locally, while the CSIT recovery is performed at the base station jointly.
Deep Learning Based MIMO Communications
A novel physical layer scheme for single user Multiple-Input Multiple-Output (MIMO) communications based on unsupervised deep learning using an autoencoder is introduced and demonstrates significant potential for learning schemes which approach and exceed the performance of the methods which are widely used in existing wireless MIMO systems.
Compressive sensing based channel feedback protocols for spatially-correlated massive antenna arrays
This paper proposes channel feedback reduction techniques based on the theory of compressive sensing, which permits the transmitter to obtain channel information with acceptable accuracy under substantially reduced feedback load.
Downlink Training Techniques for FDD Massive MIMO Systems: Open-Loop and Closed-Loop Training With Memory
Practical open-loop and closed-loop training frameworks are proposed that offer better performance in the data communication phase, especially when the signal-to-noise ratio is low, the number of transmit antennas is large, or prior channel estimates are not accurate at the beginning of the communication setup, all of which would be mostly beneficial for massive MIMO systems.
On Capacity of Large-Scale MIMO Multiple Access Channels with Distributed Sets of Correlated Antennas
In this paper, a deterministic equivalent of ergodic sum rate and an algorithm for evaluating the capacity-achieving input covariance matrices for the uplink large-scale multiple-input
Deep learning for wireless physical layer: Opportunities and challenges
This paper presents a comprehensive overview of the emerging studies on DL-based physical layer processing, including leveraging DL to redesign a module of the conventional communication system and replace the communication system with a radically new architecture based on an autoencoder.
Noncooperative Cellular Wireless with Unlimited Numbers of Base Station Antennas
  • T. Marzetta
  • Computer Science
    IEEE Transactions on Wireless Communications
  • 2010
A cellular base station serves a multiplicity of single-antenna terminals over the same time-frequency interval and a complete multi-cellular analysis yields a number of mathematically exact conclusions and points to a desirable direction towards which cellular wireless could evolve.
The COST 2100 MIMO channel model
An overview of the COST 2100 channel model is presented, including dense multipath components, polarization, and multi-link aspects, which make it suitable to model multi-user or distributed MIMO scenarios.
Message-passing algorithms for compressed sensing
A simple costless modification to iterative thresholding is introduced making the sparsity–undersampling tradeoff of the new algorithms equivalent to that of the corresponding convex optimization procedures, inspired by belief propagation in graphical models.
DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks
A novel computational sensing framework for sensing and recovering structured signals that learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals.