Downlink Channel State Information Research Articles

An efficient parallel self-attention transformer for CSI feedback

In massive multi-input multi-output (MIMO) systems, it is necessary for user equipment (UE) to transmit downlink channel state information (CSI) back to the base station (BS). As the number of antennas increases, the feedback overhead of CSI consumes a significant amount of uplink bandwidth resources. To minimize the bandwidth overhead, we propose an efficient parallel attention transformer, called EPAformer, a lightweight network that utilizes the transformer architecture and efficient parallel self-attention (EPSA) for CSI feedback tasks. The EPSA expands the attention area of each token within the transformer block effectively by dividing multiple heads into parallel groups and conducting self-attention in horizontal and vertical stripes. The proposed EPSA achieves better feature compression and reconstruction. The simulation results display that the EPAformer surpasses previous deep learning-based approaches in terms of reconstruction performance and complexity.

CSI Sensing From Heterogeneous User Feedbacks: A Constrained Phase Retrieval Approach

This paper investigates the downlink channel state information (CSI) sensing in 5G heterogeneous networks composed of user equipments (UEs) with different feedback capabilities. We aim to enhance the CSI accuracy of UEs only affording the low-resolution Type-I codebook. While existing works have demonstrated that the task can be accomplished by solving a phase retrieval (PR) formulation based on the feedback of precoding matrix indicator (PMI) and channel quality indicator (CQI), they need many feedback rounds. In this paper, we propose a novel CSI sensing scheme that can significantly reduce the feedback overhead. Our scheme involves a novel parameter dimension reduction design by exploiting the spatial consistency of wireless channels among nearby UEs, and a constrained PR (CPR) formulation that characterizes the feasible region of CSI by the PMI information. To address the computational challenge due to the non-convexity and the large number of constraints of CPR, we develop a two-stage algorithm that firstly identifies and removes inactive constraints, followed by a fast first-order algorithm. The study is further extended to multi-carrier systems. Extensive tests over DeepMIMO and QuaDriGa datasets showcase that our designs greatly outperform existing methods and achieve the high-resolution Type-II codebook performance with a few rounds of feedback.

Lightweight neural network based SNIP for CSI feedback in massive MIMO

AbstractCsiNet, a deep neural network framework, utilizes an autoencoder to efficiently transmit downlink channel state information (CSI) in the feedback link, which reduces the cost of feedback, and significantly improves the quality of the reconstruction. However, the model with massive parameters incurs a lot of storage space and high computational complexity, which is impractical for low‐cost and low‐power edge devices. In this work, a lightweight CsiNet based SNIP (Single‐shot Network Pruning) is implemented, which prunes the model using the gradient information of the first training epoch, eliminating both pretraining and the complex pruning schedule. Numerical simulation results show that, under the same compression rates, the method can achieve a similar or even better reconstruction effect and more effectively reduce computational complexity, compared to traditional lightweight methods.

Enhanced MIMO CSI Estimation Using ACCPM with Limited Feedback.

Multiple Input and Multiple Output (MIMO) is a promising technology to enable spatial multiplexing and improve throughput in wireless communication networks. To obtain the full benefits of MIMO systems, the Channel State Information (CSI) should be acquired correctly at the transmitter side for optimal beamforming design. The analytical centre-cutting plane method (ACCPM) has shown to be an appealing way to obtain the CSI at the transmitter side. This paper adopts ACCPM to learn down-link CSI in both single-user and multi-user scenarios. In particular, during the learning phase, it uses the null space beamforming vector of the estimated CSI to reduce the power usage, which approaches zero when the learned CSI approaches the optimal solution. Simulation results show our proposed method converges and outperforms previous studies. The effectiveness of the proposed method was corroborated by applying it to the scattering channel and winner II channel models.

Amplitude prediction from uplink to downlink CSI against receiver distortion in FDD systems

In frequency division duplex (FDD) massive multiple-input multiple-output (mMIMO) systems, the reciprocity mismatch caused by receiver distortion seriously degrades the amplitude prediction performance of channel state information (CSI). To tackle this issue, from the perspective of distortion suppression and reciprocity calibration, a lightweight neural network-based amplitude prediction method is proposed in this paper. Specifically, with the receiver distortion at the base station (BS), conventional methods are employed to extract the amplitude feature of uplink CSI. Then, learning along the direction of the uplink wireless propagation channel, a dedicated and lightweight distortion-learning network (Dist-LeaNet) is designed to restrain the receiver distortion and calibrate the amplitude reciprocity between the uplink and downlink CSI. Subsequently, by cascading, a single hidden layer-based amplitude-prediction network (Amp-PreNet) is developed to accomplish amplitude prediction of downlink CSI based on the strong amplitude reciprocity. Simulation results show that, considering the receiver distortion in FDD systems, the proposed scheme effectively improves the amplitude prediction accuracy of downlink CSI while reducing the transmission and processing delay.

Uplink Assisted MIMO Channel Feedback Method Based on Deep Learning.

In order to solve the problem wherein too many base station antennas are deployed in a massive multiple-input-multiple-output system, resulting in high overhead for downlink channel state information feedback, this paper proposes an uplink-assisted channel feedback method based on deep learning. The method applies the reciprocity of the uplink and downlink, uses uplink channel state information in the base station to help users give feedback on unknown downlink information, and compresses and restores the channel state information. First, an encoder-decoder structure is established. The encoder reduces the network depth and uses multi-resolution convolution to increase the accuracy of channel state information extraction while reducing the number of computations relating to user equipment. Afterward, the channel state information is compressed to reduce feedback overhead in the channel. At the decoder, with the help of the reciprocity of the uplink and downlink, the feature extraction of the uplink's magnitudes is carried out, and the downlink channel state information is integrated into a channel state information feature matrix, which is restored to its original size. The simulation results show that compared with CSINet, CRNet, CLNet, and DCRNet, indoor reconstruction precision was improved by an average of 16.4%, and outside reconstruction accuracy was improved by an average of 21.2% under all compressions.

Deep data hiding‐based channel state information feedback within audio signals

AbstractDeep learning‐based channel state information (CSI) hiding within images has been introduced to eliminate the downlink CSI feedback overhead in frequency division duplexing systems. In this letter, a deep data hiding‐based CSI feedback framework (named Au_EliCsiNet), which hides/superimposes downlink CSI within the transmitted audio signals, is proposed. Convolution neural networks are adopted to extract CSI features, hide CSI within audio signals, and reconstruct CSI from the audio signals. Simulation results show that the proposed Au_EliCsiNet can feed back downlink CSI accurately with no (or fewer) effects on the original audio transmission.

CCA-Net: A Lightweight Network Using Criss-Cross Attention for CSI Feedback

To enhance the performance of a massive multiple-input multiple-output (MIMO) system, the downlink channel state information (CSI) should be compressed and fed back to the base station (BS) effectively in a frequency division duplex (FDD) mode. In contrast to traditional compression methods that rely on the particular prior assumptions, deep learning (DL) based CSI feedback has the potential to learn informatively from the hidden complex models behind the data. However, most of the current DL based methods stay in the early stage that uses DL modules directly from image processing, while the distinctive channel semantic information has been largely ignored. In this letter, considering the spatial-temporal correlation property of CSI matrices, we propose an architecture based on criss-cross attention, called CCA-Net, which extracts the channel features more precisely by leveraging the contextual information along the delay and angle domain. Meanwhile, a real and imaginary part combination module is used to assist in extracting the internal features of CSI. In addition, to reap the computational resources at BSs, a scalable decoder is designed to extend the reconstruction abilities. Experiments demonstrate that our network achieves better normalized mean square error with lower flops than existing state-of-the-art algorithms.

Adversarial training-aided time-varying channel prediction for TDD/FDD systems

In this paper, a time-varying channel prediction method based on conditional generative adversarial network (CPcGAN) is proposed for time division duplexing/frequency division duplexing (TDD/FDD) systems. CPcGAN utilizes a discriminator to calculate the divergence between the predicted downlink channel state information (CSI) and the real sample distributions under a conditional constraint that is previous uplink CSI. The generator of CPcGAN learns the function relationship between the conditional constraint and the predicted downlink CSI and reduces the divergence between predicted CSI and real CSI. The capability of CPcGAN fitting data distribution can capture the time-varying and multipath characteristics of the channel well. Considering the propagation characteristics of real channel, we further develop a channel prediction error indicator to determine whether the generator reaches the best state. Simulations show that the CPcGAN can obtain higher prediction accuracy and lower system bit error rate than the existing methods under the same user speeds.

Machine Learning-Based CSI Feedback With Variable Length in FDD Massive MIMO

To fully unlock the benefits of multiple-input multiple-output (MIMO) networks, downlink channel state information (CSI) is required at the base station (BS). In frequency division duplex (FDD) systems, the CSI is acquired through a feedback signal from the user equipment (UE). However, this may lead to an important overhead in FDD massive MIMO systems. Focusing on these systems, in this study, we propose a novel strategy to design the CSI feedback. Our strategy allows to optimally design variable length feedback, that is promising compared to fixed feedback since users experience channel matrices differently sparse. Specifically, principal component analysis (PCA) is used to compress the channel into a latent space with adaptive dimensionality. To quantize this compressed channel, the feedback bits are smartly allocated to the latent space dimensions by minimizing the normalized mean squared error (NMSE) distortion. Finally, the quantization codebook is determined with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -means clustering. Numerical simulations show that our strategy improves the zero-forcing beamforming sum rate by 17%, compared to CsiNetPro. The number of model parameters is reduced by 23.4 times, thus causing a significantly smaller offloading overhead. At the same time, PCA is characterized by a lightweight unsupervised training, requiring eight times fewer training samples than CsiNetPro.

Reciprocity evaluation based adaptive CCM reconstruction in FDD multi-antenna systems

In view of the difficulty of obtaining downlink channel state information, partial reciprocity based channel covariance matrix (CCM) reconstruction has attracted a lot of attention in frequency division duplex (FDD) multi-antenna systems. Taking both the impact of CCM reconstruction on system performance and design complexity, we investigate an adaptive CCM reconstruction in this paper. Specifically, to effectively evaluate the validity of the reciprocity, we firstly analyze the characteristics of the partial reciprocity and define a reciprocity evaluation criterion. Then, we propose a partial antenna based angular power spectrum (APS) estimating algorithm to further reduce the complexity of the CCM reconstruction. Finally, simulation results demonstrate the superiority of our proposed schemes.

Joint Sparse Autoencoder Based Massive MIMO CSI Feedback

In frequency division duplex (FDD) based massive multiple-input multiple-output (MIMO) systems, the channel state information (CSI) feedback overhead could degrade spectrum and energy efficiency. Many works have made great progress in efficient feedback. However, previous deep learning (DL)-based CSI feedback schemes considered downlink CSI only, or exploited uplink CSI in a simple way. In this letter, we propose a neural network to compress and accurately recover downlink CSI, based on FDD angle and delay reciprocity between bi-directional channels. We design a joint sparse autoencoder to learn sparse transform for compression, and introduce auxiliary uplink CSI in an explainable approach. Numerical results demonstrate that our structure can improve the reconstruction quality compared with downlink-only structure.

Deep Learning-Based Downlink Channel Estimation for FDD Massive MIMO Systems

This letter is concerned with the downlink channel estimation in frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) system. With the number of antennas increased, acquiring the downlink channel state information (CSI) becomes complex, thus restricts the performance of communication systems. A deep learning based algorithm is used to estimate the downlink CSI without the feedback. In the proposed method, the uplink cluster is firstly obtained from the receiving signals. Based on the uplink cluster data, the downlink channel is then estimated by a neural network. Simulation results show that the proposed algorithm can achieve higher achievable spectral efficiency.

Deep learning-based massive MIMO channel estimation with reduced feedback

The downlink channel state information (CSI) must be available on the base station (BS) side to take advantage of all the features of massive multiple-input multiple-output (MIMO) systems. The channel estimation in massive MIMO systems is a challenging task because of the huge pilot and feedback overhead due to the large size of antennas. In this paper, we have proposed a multi task deep network for the channel estimation with the aim of decreasing the pilot and feedback overhead. An encoder network is designed to compress the received signal and reduce the feedback overhead. Furthermore, a decoder network is developed to reconstruct the compressed feedback. The estimator network is suggested to provide the channel estimation from the reconstructed feedback. The performance of the presented scheme has been evaluated in various simulation scenarios. The results confirm that the proposed method is capable of estimating the channel more accurately than the contemporary works. Moreover, this method has reduced the feedback and pilot overhead to a great extent.

Downlink CSI Recovery in Massive MIMO Systems by Proactive Sensing

Accurate channel state information (CSI) is critical to harvest the potential gain brought by massive multiple-input multiple-output (MIMO). However, the acquisition of downlink CSI is challenging in the frequency division duplex (FDD) systems due to limited feedback and the use of low-resolution codebooks. In this letter, we propose a novel sensing-assisted CSI recovery (SACR) scheme, where the BS proactively senses the downlink channel structure so that accurate CSI recovery at the BS can be achieved with only a few number of low-resolution user feedbacks. Numerical results show that the proposed scheme significantly outperforms the existing methods.

AcsiNet: Attention-Based Deep Learning Network for CSI Prediction in FDD MIMO Systems

In 5G frequency division duplex (FDD) systems, the user equipment needs to feedback the measured downlink channel state information (CSI) to the base station to improve the throughput. For massive multiple-input-multiple-output (MIMO) systems, each antenna in base station needs its CSI feedback, which results in significant transmission overhead and latency. We propose an attention-based deep learning network to directly predict the downlink CSI from the corresponding uplink one, eliminating the feedback overhead completely. Specifically, the uplink CSI is first compressed based on the 3D inverse discrete Fourier transform, then is fed into an attention-based deep learning network which can focus on key CSI characteristics. The simulation results show that the proposed method achieves high prediction accuracy and low complexity, indicating prospective applications in FDD massive MIMO systems.

PEACH: Proactive and Environment-Aware Channel State Information Prediction with Depth Images

Up-to-date and accurate prediction of Channel State Information (CSI) is of paramount importance in Ultra-Reliable Low-Latency Communications (URLLC), specifically in dynamic environments where unpredictable mobility is inherent. CSI can be meticulously tracked by means of frequent pilot transmissions, which on the downside lead to an increase in metadata (overhead signaling) and latency, which are both detrimental for URLLC. To overcome these issues, in this paper, we take a fundamentally different approach and propose PEACH, a machine learning system which utilizes environmental information with depth images to predict CSI amplitude in beyond 5G systems, without requiring metadata radio resources, such as pilot overheads or any feedback mechanism. PEACH exploits depth images by employing a convolutional neural network to predict the current and the next 100 ms CSI amplitudes. The proposed system is experimentally validated with extensive measurements conducted in an indoor environment, involving two static receivers and two transmitters, one of which is placed on top of a mobile robot. We prove that environmental information can be instrumental towards proactive CSI amplitude acquisition of both static and mobile users on base stations, while providing an almost similar performance as pilot-based methods, and completely avoiding the dependency on feedback and pilot transmission for both downlink and uplink CSI information. Furthermore, compared to demodulation reference signal based traditional pilot estimation in ideal conditions without interference, our experimental results show that PEACH yields the same performance in terms of average bit error rate when channel conditions are poor (using low order modulation), while not being much worse when using higher modulation orders, like 16-QAM or 64-QAM. More importantly, in the realistic cases with interference taken into account, our experiments demonstrate considerable improvements introduced by PEACH in terms of normalized mean square error of CSI amplitude estimation, up to 6 dB, when compared to traditional approaches.

Deep-Unfolding-Based Bit-Level CSI Feedback in Massive MIMO Systems

In frequency division duplex mode, downlink channel state information (CSI) should be sent to the base station via a feedback link to obtain the benefits of the massive multiple-input multiple-output technology, leading to a substantial overhead. The existing deep-unfolding-based works combine the advantages of high performance and interpretability. In practical systems, the compressed CSI must be quantized at the user equipment before feedback. In this letter, a deep-unfolding-based bit-level CSI feedback is proposed to reduce the effects of quantization errors by using the shortcut and approximate quantization schemes. The shortcut scheme provides the unquantized encoder output directly to the decoder through an additional network branch, which can effectively help the decoder training. The approximate quantization scheme allows the gradient to be propagated correctly by approximating the real quantization operation. The two schemes are combined as a training strategy to reduce quantization errors further. Results show that the combined scheme can substantially reduce the influence of the quantization layer and improve the reconstruction performance while having some generality.

Learning-Based MIMO Channel Estimation Under Practical Pilot Sparsity and Feedback Compression

Wireless links using massive MIMO transceivers are vital for next generation wireless communications networks. Precoding in Massive MIMO transmission requires accurate downlink channel state information (CSI). Many recent works have effectively applied deep learning (DL) to jointly train UE-side compression networks for delay domain CSI and a BS-side decoding scheme. Vitally, these works assume that the full delay domain CSI is available at the UE, but in reality, the UE must estimate the delay domain based on a limited number of frequency domain pilots. In this work, we propose a linear pilot-to-delay estimator (P2DE) that acquires the truncated delay CSI via sparse frequency pilots. We show the accuracy of the P2DE under frequency downsampling, and we demonstrate the P2DE’s efficacy when utilized with existing CSI estimation networks. Additionally, we propose to use trainable compressed sensing (CS) networks in a differential encoding network for time-varying CSI estimation, and we propose a new network, MarkovNet-ISTA-ENet (MN-IE), which combines a CS network for initial CSI estimation and multiple autoencoders to estimate the error terms. We demonstrate that MN-IE has better asymptotic performance than networks comprised of only one type of network.

Deep learning for joint channel estimation and feedback in massive MIMO systems

The great potentials of massive Multiple-Input Multiple-Output (MIMO) in Frequency Division Duplex (FDD) mode can be fully exploited when the downlink Channel State Information (CSI) is available at base stations. However, the accurate CSI is difficult to obtain due to the large amount of feedback overhead caused by massive antennas. In this paper, we propose a deep learning based joint channel estimation and feedback framework, which comprehensively realizes the estimation, compression, and reconstruction of downlink channels in FDD massive MIMO systems. Two networks are constructed to perform estimation and feedback explicitly and implicitly. The explicit network adopts a multi-Signal-to-Noise-Ratios (SNRs) technique to obtain a single trained channel estimation subnet that works well with different SNRs and employs a deep residual network to reconstruct the channels, while the implicit network directly compresses pilots and sends them back to reduce network parameters. Quantization module is also designed to generate data-bearing bitstreams. Simulation results show that the two proposed networks exhibit excellent performance of reconstruction and are robust to different environments and quantization errors.