Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems

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

750 citations recorded by the source corpus.

Channel estimation is very challenging when the receiver is equipped with a limited number of radio-frequency (RF) chains in beamspace millimeter-wave massive multiple-input and multiple-output systems. To solve this problem, we exploit a learned denoising-based approximate message passing (LDAMP) network. This neural network can learn channel structure and estimate channel from a large number of training data. Furthermore, we provide an analytical framework on the asymptotic performance of the channel estimator. Based on our analysis and simulation results, the LDAMP neural network significantly outperforms state-of-the-art compressed sensing-based algorithms even when the receiver is equipped with a small number of RF chains.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/8d7bfe1ec3a7fa2af466126d875d1fcbf7885d1f

How researchers see this paper

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

In Aerospace Engineering

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

A Tutorial on Fluid Antenna System for 6G Networks: Encompassing Communication Theory, Optimization Methods and Hardware Designs (2024, background): “Note that recent study of channel estimation/extrapolation using deep learning has primarily focused on mechanisms such as MLP-like [138], [139], [140], [141], [142], attention [143], CNN-like [144], long short-term memory (LSTM)-like [145], and etc.”
Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels (2018, methodology): “resolution degrades and the feedback overhead cannot reduce any more in fast-changing channels. Recently, deep learning (DL) methods has been successfully applied in wireless communications [4], [5], [6]. A CSI feedback network, called CsiNet [7], uses an autoencoderlike architecture to mimic the CS”
Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems (2019, methodology): “In [16], iterative channel estimation has been proposed for the lens mmWave massive MIMO systems, where denoising neural network (NN) is used in each iteration to update the estimated channel.”
Deep Learning in Physical Layer Communications (2018, background): “Learned denoising-based AMP (LDAMP) [6] is one of the best signal recovery algorithms in terms of both accuracy and speed, which has been applied to channel estimation in millimeter-wave (mmWave) communications [7].”
Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces (2020, background): “There have been some denoiser-based channel estimators proposed for enhanced performance [17], where the real-part and imaginary-part of complex-valued data are processed independently.”
Model-Driven Deep Learning for MIMO Detection (2020, background): “Recently, it has been applied in physical layer communications [11]–[13], such as channel estimation [14]–[16], CSI feedback [17], signal detection [18]–[26], channel coding [27], [28], and end-to-end transceiver design [29], [30].”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, methodology): “One of the potential applications of employing DL methods in such mmWave M-MIMO systems is the estimation of radio channel quality [23], which is essential for the design of transmission techniques such as beamforming.”
Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial (2017, methodology): “The work in [115] used an ANN-based learning algorithm for channel estimation and channel selection.”
Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks (2017, methodology): “NNs. p Content popularity prediction. [113] FNNs. p Content request distribution prediction. [97], [114] RNNs. p Multi-RAT Resource management. [115] DNNs. p [101] RNNs. p RAT selection. [116] CNNs. p Transmission technology classiﬁcation. [117] FNNs. p Multi-radio packet scheduling. [118] RNNs. p M”
Deep Learning-Based Channel Estimation (2018, methodology): “ implicitly. More speciﬁcally, this method is not able to explicitly ﬁnd the channel time-frequency response and so not effective for applications which need to have the complete channel response. In [9], the channel matrix is considered as an image and then used a denoising network for channel esti”
Machine Learning in the Air (2019, background): “In [29], [30], it is shown that these estimators can even outperform estimators based on sparse signal recovery, when trained with sufﬁcient amount of data.”
Model-Driven Deep Learning for Physical Layer Communications (2018, methodology): “The LDAMP network proposed in [17] can be interpreted as a specialized model-driven DL architecture for channel estimation that inherits the superiority of iterative signal recovery algorithms and uses CNN to learn the channel structure.”
A Tutorial on Extremely Large-Scale MIMO for 6G: Fundamentals, Signal Processing, and Applications (2023, background): “Machine learning-based channel estimation meth-ods can be divided into two categories: model-driven [172], [173] and data-driven [174], [175].”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, methodology): “Recently, deep learning has been applied to refine the traditional block-structure communication systems, including the multiple-input and multipleoutput (MIMO) detection [2], [3], channel decoding [4]–[9], and channel estimation [10], [11].”