Deep learning for 1-bit compressed sensing-based superimposed CSI feedback

Unlike the time-division duplexing (TDD) systems, the downlink (DL) and uplink (UL) channels are not reciprocal anymore in the case of frequency-division duplexing (FDD). However, some long-term parameters, e.g. the time delays and angles of arrival (AoAs) of the channel paths, still enjoy reciprocity. In this paper, by efficiently exploiting the aforementioned limited reciprocity, we address the DL channel state information (CSI) feedback in a practical wideband massive multiple-input multiple-output (MIMO) system operating in the FDD mode. In particular, the base station (BS) can transmit the FFT-based pilots with the carefully-selected phase shifts to align the DL paths. Then the user can rely on the so-called time-domain aggregate channel (TAC) to derive the estimate of the DL CSI. Next, with the knowledge about the second-order statistics of the DL channels, the user is also able to compute feedback of reduced dimensionality. We demonstrate that each user can just feed back one scalar number per DL channel path for the BS to recover the DL CSIs. Comprehensive numerical results corroborate our designs.

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.

In the multiuser multiple-input multiple-output (MU-MIMO) system, to reduce the influence of channel correlation on system performance, the base station (BS) should select the appropriate subset of user equipments (UEs) according to their channel state information (CSI). Due to a lack of channel reciprocity, the downlink CSI needs to be fed back to the BS in frequency division duplexing (FDD) mode. Some scholars have exploited kinds of deep neural networks (DNNs) for sensing and recovering CSI. However, user selection after all the CSI is reconstructed by DNNs will bring a great time delay. In this paper, we propose a deep learning-based CSI feedback scheme called US-CsiNet. Based on adversarial autoencoder (AAE), US-CsiNet can explicitly cover user schedule information while representing CSI. At the UE side, the encoder of US-CsiNet maps the CSI into codewords of which part are feature information for user schedule. Then the BS applies these partial codewords to separate the UEs into different groups and select active UEs. Finally, the decoder of AAE reconstructs the CSI of these active UEs. US-CsiNet can not only simplify the user selection process but also guarantee the accuracy of CSI reconstruction. The simulation results show that the proposed approach outperforms maximum channel gain (MCG) user selection algorithms and achieves the nearly same performance with semiorthogonal user selection (SUS) which needs full CSI of all users at the BS.

Closed-loop MIMO system can provide dramatic gains in channel capacity. However, mobile terminal (MT) must feedback the downlink channel state information (CSI) to Base station (BS), and transmitting CSI is a heavy burden consuming considerable uplink bandwidth. To address this bottleneck problem, a zero-overhead downlink CSI feedback scheme is proposed in this paper. After receiving the downlink pilots, MT directly superposes the uplink pilot on the received analog downlink pilot, forms the hybrid pilot (HP), and then transmits HP to BS via uplink pilot channel. Because downlink CSI can be recovered from HP at BS, and HP is fed back to BS via the uplink pilot channel, no extra uplink channel is occupied and the overhead for CSI feedback is zero. Moreover, since no CSI estimation process is performed at MT, the terminal's complexity can be reduced. Numerical Simulations verify that, the proposed downlink CSI feedback has the higher precision than the traditional feedback schemes, and the MSE of CSI feedback can be reduced significantly.

Due to the discarding of downlink channel state information (CSI) amplitude and the employing of iteration reconstruction algorithms, 1-bit compressed sensing (CS)-based superimposed CSI feedback is challenged by low recovery accuracy and large processing delay. To overcome these drawbacks, this letter proposes a fusion learning scheme by exploiting the bi-directional channel reciprocity. Specifically, a simplified version of the conventional downlink CSI reconstruction is utilized to extract the initial feature of downlink CSI, and a single hidden layer-based amplitude-learning network (AMPL-NET) is designed to learn the auxiliary feature of the downlink CSI amplitude. Then, based on the extracted and learned amplitude features, a simple but effective amplitude-fusion network (AMPF-NET) is developed to perform the amplitude fusion of downlink CSI and thus improves the reconstruction accuracy for 1-bit CS-based superimposed CSI feedback while reducing the processing delay. Simulation results show the effectiveness of the proposed feedback scheme and the robustness against parameter variations.

For massive multiple-input multiple-output (MIMO) systems, downlink channel state information (CSI) feedback is critical for exploiting the performance potentials. Recognized by the 3rd Generation Partnership Project as a key use case for the artificial intelligence-native air interface, deep learning (DL)-based CSI feedback has attracted extensive research from academia and industry. However, one of the most significant obstacles to its practical deployment is the limited generalization capabilities of DL models. In this article, we first illustrate the generalization challenge faced by DL-based CSI feedback with the main factors. Then, we systematically analyze its feasible solutions from two perspectives: initial model acquisition and efficient online updating. Finally, to address knowledge-forgetting problems in online updating, a novel alternating optimization framework is proposed to further improve the generalization ability through knowledge review. Hopefully, this article can give inspiring insights for the optimization of deployment and generalization for DL-based CSI feedback systems.

In frequency division duplex mode of massive multiple-input multiple-output systems, the downlink channel state information (CSI) must be sent to the base station (BS) through a feedback link. However, transmitting CSI to the BS is costly due to the bandwidth limitation of the feedback link. Deep learning (DL) has recently achieved remarkable success in CSI feedback. Realizing high-performance and low-complexity CSI feedback is a challenge in DL-based communication. We develop a DL-based CSI feedback network in this study to complete the feedback of CSI effectively. However, this network cannot be effectively applied to the mobile terminal due to its excessive number of parameters and high computational complexity. Therefore, we further propose a new lightweight CSI feedback network based on the developed network. Simulation results show that the proposed CSI network maintains a few parameters and parameter complexity while exhibiting better reconstruction performance than existing works. These findings suggest the feasibility and potential of the proposed techniques.

Accurate downlink channel state information (CSI) is required to be fed back to the base station (BS) in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems in order to achieve maximum antenna diversity and multiplexing. However, downlink CSI feedback overhead scales with the number of transceiver antennas, a major hurdle for practical deployment of FDD massive MIMO systems. To solve this problem, we propose a compressive sampled CSI feedback method based on deep learning (SampleDL). In SampleDL, the massive MIMO channel matrix is sampled uniformly in time/frequency dimension before being fed into neural networks (NNs), which will reduce the computational resource/time at user equipment (UE) as well as enhance the CSI recovery accuracy at the BS. Both theoretical analysis and normalized mean square errors (NMSE) results confirm the advantages of the proposed method in terms of time complexity and recovery accuracy. Besides, a suitable CSI feedback period is explored by link level simulations, which aims to further reduce the overhead of CSI feedback without degrading the communication quality.

In a massive multiple-input multiple-output (MIMO) system, channel state information (CSI) is essential for the base station (BS) to achieve high performance gain. The user equipment (UE) needs to estimate CSI and then feeds it back to the BS in the frequency division duplexing (FDD) mode. Effective compression of CSI will significantly reduce the cost of channel feedback, and many deep learning (DL) based channel compression schemes have been proposed to achieve this goal. In this paper, rather than viewing CSI as images as in most existing works, we propose a new perspective of viewing CSI as an information sequence and analogize CSI feedback to a machine translation task. Further, we propose a novel sequence to sequence (Seq2Seq) model for CSI feedback composed of only recurrent neural networks and a small-scale fully connected layer, avoiding the convolution and pooling structure commonly used in current DL-based works. The advantage of this scheme is that it fully integrates the physical characteristics of the MIMO channel in the spatial domain into the structure of the neural network and avoids the loss of some prominent unsmooth or discontinuous features caused by the inappropriate convolution and pooling operation. Simulation results show that the proposed Seq2Seq model outperforms other DL-based CSI compression techniques under various communication scenarios.

Massive multiple-input multiple-output (massive-MIMO) is considered as the key technology to meet the huge demands of data rates in the future wireless communications networks. However, for massive-MIMO systems to realize their maximum potential gain, sufficiently accurate downlink (DL) channel state information (CSI) with low overhead to meet the short coherence time (CT) is required. Therefore, this article aims to overcome the technical challenge of DL CSI estimation in a frequency-division-duplex (FDD) massive-MIMO with short CT considering five different physical correlation models. To this end, the statistical structure of the massive-MIMO channel, which is captured by the physical correlation is exploited to find sufficiently accurate DL CSI estimation. Specifically, to reduce the DL CSI estimation overhead, the training sequence is designed based on the eigenvectors of the transmit correlation matrix. To this end, the achievable sum rate (ASR) maximization and the mean square error (MSE) of CSI estimation with short CT are investigated using the proposed training sequence design. Furthermore, this article examines the effect of channel hardening in an FDD massive-MIMO system. The results demonstrate that in high correlation scenarios, a large loss in channel hardening is obtained. The results reveal that increasing the correlation level reduces the MSE but does not increase the ASR. However, exploiting the spatial correction structure is still very essential for the FDD massive-MIMO systems under limited CT. This finding holds for all the physical correlation models considered.

In modern wireless systems, the feedback of DownLink (DL) Channel State Information (CSI) from User Equipment (UE) to Base Stations (BS) may require substantial computational and feedback bandwidth overheads. A promising approach to improve feedback efficiency is to leverage side information which is correlated to DL CSI. Despite potential of doing so, critical aspects remain underexplored in current research, particularly the quantification of the benefits and the inherent limitations of utilizing side information. This paper addresses these gaps by introducing a novel algorithm to compute the rate-distortion function for general compression scenarios incorporating side information. We apply this algorithm to the DL CSI feedback problem having UL CSI as the side information and generate rate-distortion functions. Using the estimated rate-distortion functions, we measure the gain of side information over diverse feedback rates and UE mobility profiles. The results reveal that the benefits of leveraging side information are particularly significant for UEs characterized by high mobility and constrained to operate at low feedback overheads.

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.

Chapter 7 - Channel feedback for mmWave massive MIMO

Massive multiple-input multiple-output systems deploying a large number of antennas at the base station considerably increase the spectrum efficiency by serving multiple users simultaneously without causing severe interference. However, the advantage relies on the availability of the downlink channel state information (CSI) of multiple users, which is still a challenge in frequency-division-duplex transmission systems. This paper aims to solve this problem by developing a full transceiver framework that includes downlink channel training (or estimation), CSI feedback, and channel reconstruction schemes. Our framework provides accurate reconstruction results for multiple users with small amounts of training and feedback overhead. Specifically, we first develop an enhanced Newtonized orthogonal matching pursuit (eNOMP) algorithm to extract the frequency-independent parameters (i.e., downtilts, azimuths, and delays) from the uplink. Then, by leveraging the information from these frequency-independent parameters, we develop an efficient downlink training scheme to estimate the downlink channel gains for multiple users. This training scheme offers an acceptable estimation error rate of the gains with a limited pilot amount. Numerical results verify the precision of the eNOMP algorithm and demonstrate that the sum-rate performance of the system using the reconstructed downlink channel can approach that of the system using perfect CSI.

Deep learning (DL)-based channel state information (CSI) feedback improves the capacity and energy efficiency of massive multiple-input multiple-output (MIMO) systems in frequency division duplexing mode. However, multiple neural networks with different lengths of feedback overhead are required by time-varying bandwidth resources. The storage space required at the user equipment (UE) and the base station (BS) for these models increases linearly with the number of models. In this paper, we propose a DL-based changeable-rate framework with novel quantization scheme to improve the efficiency and feasibility of CSI feedback systems. This framework can reutilize all the network layers to achieve overhead-changeable CSI feedback to optimize the storage efficiency at the UE and the BS sides. Designed quantizer in this framework can avoid the normalization and gradient problems faced by traditional quantization schemes. Specifically, we propose two DL-based changeable-rate CSI feedback networks CH- CsiNetPro and CH- DualNetSph by introducing a feedback overhead control unit. Then, a pluggable quantization block (PQB) is developed to further improve the encoding efficiency of CSI feedback in an end-to-end way. Compared with existing CSI feedback methods, the proposed framework saves the storage space by about 50% with changeable-rate scheme and improves the encoding efficiency with the quantization module.