scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Overcoming the Channel Estimation Barrier in Massive MIMO Communication via Deep Learning

TL;DR: This article develops important insights derived from the physical radio frequency (RF) channel properties and presents a comprehensive overview on the application of DL for accurately estimating channel state information (CSI) with low overhead.
Abstract: A new wave of wireless services, including virtual reality, autonomous driving and Internet of Things, is driving the design of new generations of wireless systems to deliver ultra-high data rates, massive numbers of connections and ultra-low latency. Massive multiple-input multiple-output (MIMO) is one of the critical underlying technologies that allow future wireless networks to meet these service needs. This article discusses the application of deep learning (DL) for massive MIMO channel estimation in wireless networks by integrating the underlying characteristics of channels in future high-speed cellular deployment. We develop important insights derived from the physical radio frequency (RF) channel properties and present a comprehensive overview on the application of DL for accurately estimating channel state information (CSI) with low overhead. We provide examples of successful DL application in CSI estimation for massive MIMO wireless systems and highlight several promising directions for future research.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: The aim of this paper is to assist the readers to understand different ML approaches in CM-MIMO systems, explore some of the advantages and disadvantages, identify some the open issues, and motivate the readers toward future trends.
Abstract: Machine learning (ML) which is a subset of artificial intelligence is expected to unlock the potential of challenging large-scale problems in conventional massive multiple-input-multiple-output (CM-MIMO) systems. This introduces the concept of intelligent massive MIMO (I-mMIMO) systems. Due to the surge of application of different ML techniques in the enhancement of mMIMO systems for existing and emerging use cases beyond fifth-generation (B5G) networks, this article aims to provide an overview of the different aspects of the I-mMIMO systems. First, the characteristics and challenges of the CM-MIMO have been identified. Secondly, the most recent efforts aimed at applying ML to a different aspect of CM-MIMO systems are presented. Thirdly, the deployment of I-mMIMO and efforts towards standardization are discussed. Lastly, the future trends of I-mMIMO-enabled application systems are presented. The aim of this paper is to assist the readers to understand different ML approaches in CM-MIMO systems, explore some of the advantages and disadvantages, identify some of the open issues, and motivate the readers toward future trends.

5 citations

Journal ArticleDOI
TL;DR: In this article , the authors present the advancements to the date of digital SIC approaches and highlights the advantages and limitations of each approach and summarize different hardware platforms used for SIC along with their key features.

4 citations

References
More filters
Journal ArticleDOI
TL;DR: The learned denoising-based approximate message passing (LDAMP) network is exploited and significantly outperforms state-of-the-art compressed sensing-based algorithms even when the receiver is equipped with a small number of RF chains.
Abstract: 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.

587 citations


"Overcoming the Channel Estimation B..." refers methods in this paper

  • ...Channel estimation Accuracy enhancement [6], denoising [9, 10],...

    [...]

  • ...In [10], a denoising CNN has been designed to enhance the performance of the approximate message passing (AMP) algorithm, which can recover the high-dimensional beamspace massive MIMO channel that exhibits sparsity with low computational complexity....

    [...]

Journal ArticleDOI
TL;DR: The COST 2100 channel model is a geometry-based stochastic channel model (GSCM) that can reproduce MIMO channels over time, frequency, and space as mentioned in this paper.
Abstract: The COST 2100 channel model is a geometry- based stochastic channel model (GSCM) that can reproduce the stochastic properties of MIMO channels over time, frequency, and space. In contrast to other popular GSCMs, the COST 2100 approach is generic and flexible, making it suitable to model multi-user or distributed MIMO scenarios. In this article a concise overview of the COST 2100 channel model is presented. Main concepts are described, together with useful implementation guidelines. Recent developments, including dense multipath components, polarization, and multi-link aspects, are also discussed.

544 citations

Journal ArticleDOI
TL;DR: In this article, a deep learning-based CSI sensing and recovery mechanism is proposed to learn to effectively use channel structure from training samples, which can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing-based methods.
Abstract: 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 transformation from CSI to a near-optimal number of representations (or codewords) and an inverse transformation from codewords to CSI. We perform experiments to demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.

513 citations

Posted Content
TL;DR: In this article, a novel CSI sensing and recovery network that learns to effectively use channel structure from training samples is proposed. But, the CSI reconstruction quality is not significantly improved compared with existing compressive sensing (CS)-based methods.
Abstract: In frequency division duplex mode, the downlink channel state information (CSI) should be conveyed to the base station through feedback links so that the potential gains of a massive multiple-input multiple-output can be exhibited. However, the excessive feedback overhead remains a bottleneck in this regime. In this letter, we use beep learning technology to develop CsiNet, a novel CSI sensing and recovery network that learns to effectively use channel structure from training samples. In particular, CsiNet learns a transformation from CSI to a near-optimal number of representations (codewords) and an inverse transformation from codewords to CSI. Experiments demonstrate that CsiNet can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods. Even at excessively low compression regions where CS-based methods cannot work, CsiNet retains effective beamforming gain.

395 citations

Journal ArticleDOI
TL;DR: The results in this paper clearly demonstrate that deep CNN can efficiently exploit channel correlation to improve the estimation performance for mmWave massive MIMO systems.
Abstract: For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is usually used to reduce the complexity and cost, which poses a very challenging issue in channel estimation. In this paper, deep convolutional neural network (CNN) is employed to address this problem. We first propose a spatial-frequency CNN (SF-CNN) based channel estimation exploiting both the spatial and frequency correlation, where the corrupted channel matrices at adjacent subcarriers are input into the CNN simultaneously. Then, exploiting the temporal correlation in time-varying channels, a spatial-frequency-temporal CNN (SFT-CNN) based approach is developed to further improve the accuracy. Moreover, we design a spatial pilot-reduced CNN (SPR-CNN) to save spatial pilot overhead for channel estimation, where channels in several successive coherence intervals are grouped and estimated by a channel estimation unit with memory. Numerical results show that the proposed SF-CNN and SFT-CNN based approaches outperform the non-ideal minimum mean-squared error (MMSE) estimator but with reduced complexity, and achieve the performance close to the ideal MMSE estimator that is very difficult to be implemented in practical situations. They are also robust to different propagation scenarios. The SPR-CNN based approach achieves comparable performance to SF-CNN and SFT-CNN based approaches while only requires about one-third of spatial pilot overhead at the cost of complexity. The results in this paper clearly demonstrate that deep CNN can efficiently exploit channel correlation to improve the estimation performance for mmWave massive MIMO systems.

257 citations


"Overcoming the Channel Estimation B..." refers background or methods in this paper

  • ...pilot reduction [6], mixed-resolution ADCs [7] Pilot reduction [6],...

    [...]

  • ...Channel estimation Accuracy enhancement [6], denoising [9, 10],...

    [...]

  • ...In [6], a spatial pilot-reduced CNN (SPR-CNN) is designed to save spatial pilot overhead for massive MIMO-OFDM channel estimation....

    [...]