arXiv subjects

Caijun Zhong

Publications and source records attributed to Caijun Zhong.

At least 37 records · Page 2Linked to original sources

arXiv2022

Integrating Sensing, Computing, and Communication in 6G Wireless Networks: Design and Optimization

The roll-out of various emerging wireless services has triggered the need for the sixth-generation (6G) wireless networks to provide functions of target sensing, intelligent computing and information communication over the same radio spectrum. In this paper, we provide a unified framework integrating sensing, computing, and communication to optimize limited system resource for 6G wireless networks. In particular, two typical joint beamforming design algorithms are derived based on multi-objective optimization problems (MOOP) with the goals of the weighted overall performance maximization and the total transmit power minimization, respectively. Extensive simulation results validate the effectiveness of the proposed algorithms. Moreover, the impacts of key system parameters are revealed to provide useful insights for the design of integrated sensing, computing, and communication (ISCC).

cs.IT↗

arXiv2022

A Deep Learning-Based Framework for Low Complexity Multi-User MIMO Precoding Design

Using precoding to suppress multi-user interference is a well-known technique to improve spectra efficiency in multiuser multiple-input multiple-output (MU-MIMO) systems, and the pursuit of high performance and low complexity precoding method has been the focus in the last decade. The traditional algorithms including the zero-forcing (ZF) algorithm and the weighted minimum mean square error (WMMSE) algorithm failed to achieve a satisfactory trade-off between complexity and performance. In this paper, leveraging on the power of deep learning, we propose a low-complexity precoding design framework for MU-MIMO systems. The key idea is to transform the MIMO precoding problem into the multiple-input single-output precoding problem, where the optimal precoding structure can be obtained in closed-form. A customized deep neural network is designed to fit the mapping from the channels to the precoding matrix. In addition, the technique of input dimensionality reduction, network pruning, and recovery module compression are used to further improve the computational efficiency. Furthermore, the extension to the practical MIMO orthogonal frequency-division multiplexing (MIMO-OFDM) system is studied. Simulation results show that the proposed low-complexity precoding scheme achieves similar performance as the WMMSE algorithm with very low computational complexity.

cs.IT↗

arXiv2022

Deep Learning-based Channel Estimation for Wideband Hybrid MmWave Massive MIMO

Hybrid analog-digital (HAD) architecture is widely adopted in practical millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems to reduce hardware cost and energy consumption. However, channel estimation in the context of HAD is challenging due to only limited radio frequency (RF) chains at transceivers. Although various compressive sensing (CS) algorithms have been developed to solve this problem by exploiting inherent channel sparsity and sparsity structures, practical effects, such as power leakage and beam squint, can still make the real channel features deviate from the assumed models and result in performance degradation. Also, the high complexity of CS algorithms caused by a large number of iterations hinders their applications in practice. To tackle these issues, we develop a deep learning (DL)-based channel estimation approach where the sparse Bayesian learning (SBL) algorithm is unfolded into a deep neural network (DNN). In each SBL layer, Gaussian variance parameters of the sparse angular domain channel are updated by a tailored DNN, which is able to effectively capture complicated channel sparsity structures in various domains. Besides, the measurement matrix is jointly optimized for performance improvement. Then, the proposed approach is extended to the multi-block case where channel correlation in time is further exploited to adaptively predict the measurement matrix and facilitate the update of Gaussian variance parameters. Based on simulation results, the proposed approaches significantly outperform existing approaches but with reduced complexity.

cs.IT↗

arXiv2022

Online Deep Neural Network for Optimization in Wireless Communications

Recently, deep neural network (DNN) has been widely adopted in the design of intelligent communication systems thanks to its strong learning ability and low testing complexity. However, most current offline DNN-based methods still suffer from unsatisfactory performance, limited generalization ability, and poor interpretability. In this article, we propose an online DNN-based approach to solve general optimization problems in wireless communications, where a dedicated DNN is trained for each data sample. By treating the optimization variables and the objective function as network parameters and loss function, respectively, the optimization problem can be solved equivalently through network training. Thanks to the online optimization nature and meaningful network parameters, the proposed approach owns strong generalization ability and interpretability, while its superior performance is demonstrated through a practical example of joint beamforming in intelligent reflecting surface (IRS)-aided multi-user multiple-input multiple-output (MIMO) systems. Simulation results show that the proposed online DNN outperforms conventional offline DNN and state-of-the-art iterative optimization algorithm, but with low complexity.

cs.IT↗

arXiv2022

Deep Learning based Channel Estimation for Massive MIMO with Hybrid Transceivers

Accurate and efficient estimation of the high dimensional channels is one of the critical challenges for practical applications of massive multiple-input multiple-output (MIMO). In the context of hybrid analog-digital (HAD) transceivers, channel estimation becomes even more complicated due to information loss caused by limited radio-frequency chains. The conventional compressive sensing (CS) algorithms usually suffer from unsatisfactory performance and high computational complexity. In this paper, we propose a novel deep learning (DL) based framework for uplink channel estimation in HAD massive MIMO systems. To better exploit the sparsity structure of channels in the angular domain, a novel angular space segmentation method is proposed, where the entire angular space is segmented into many small regions and a dedicated neural network is trained offline for each region. During online testing, the most suitable network is selected based on the information from the global positioning system. Inside each neural network, the region-specific measurement matrix and channel estimator are jointly optimized, which not only improves the signal measurement efficiency, but also enhances the channel estimation capability. Simulation results show that the proposed approach significantly outperforms the state-of-the-art CS algorithms in terms of estimation performance and computational complexity.

cs.IT↗

arXiv2021

Unsourced Random Massive Access with Beam-Space Tree Decoding

The core requirement of massive Machine-Type Communication (mMTC) is to support reliable and fast access for an enormous number of machine-type devices (MTDs). In many practical applications, the base station (BS) only concerns the list of received messages instead of the source information, introducing the emerging concept of unsourced random access (URA). Although some massive multiple-input multiple-output (MIMO) URA schemes have been proposed recently, the unique propagation properties of millimeter-wave (mmWave) massive MIMO systems are not fully exploited in conventional URA schemes. In grant-free random access, the BS cannot perform receive beamforming independently as the identities of active users are unknown to the BS. Therefore, only the intrinsic beam division property can be exploited to improve the decoding performance. In this paper, a URA scheme based on beam-space tree decoding is proposed for mmWave massive MIMO system. Specifically, two beam-space tree decoders are designed based on hard decision and soft decision, respectively, to utilize the beam division property. They both leverage the beam division property to assist in discriminating the sub-blocks transmitted from different users. Besides, the first decoder can reduce the searching space, enjoying a low complexity. The second decoder exploits the advantage of list decoding to recover the miss-detected packets. Simulation results verify the superiority of the proposed URA schemes compared to the conventional URA schemes in terms of error probability.

cs.IT↗

arXiv2021

C-GRBFnet: A Physics-Inspired Generative Deep Neural Network for Channel Representation and Prediction

In this paper, we aim to efficiently and accurately predict the static channel impulse response (CIR) with only the user's position information and a set of channel instances obtained within a certain wireless communication environment. Such a problem is by no means trivial since it needs to reconstruct the high-dimensional information (here the CIR everywhere) from the extremely low-dimensional data (here the location coordinates), which often results in overfitting and large prediction error. To this end, we resort to a novel physics-inspired generative approach. Specifically, we first use a forward deep neural network to infer the positions of all possible images of the source reflected by the surrounding scatterers within that environment, and then use the well-known Gaussian Radial Basis Function network (GRBF) to approximate the amplitudes of all possible propagation paths. We further incorporate the most recently developed sinusoidal representation network (SIREN) into the proposed network to implicitly represent the highly dynamic phases of all possible paths, which usually cannot be well predicted by the conventional neural networks with non-periodic activators. The resultant framework of Cosine-Gaussian Radial Basis Function network (C-GRBFnet) is also extended to the MIMO channel case. Key performance measures including prediction accuracy, convergence speed, network scale and robustness to channel estimation error are comprehensively evaluated and compared with existing popular networks, which show that our proposed network is much more efficient in representing, learning and predicting wireless channels in a given communication environment.

eess.SP↗

arXiv2021

Exploiting Simultaneous Low-Rank and Sparsity in Delay-Angular Domain for Millimeter-Wave/Terahertz Wideband Massive Access

Millimeter-wave (mmW)/Terahertz (THz) wideband communication employing a large-scale antenna array is a promising technique of the sixth-generation (6G) wireless network for realizing massive machine-type communications (mMTC). To reduce the access latency and the signaling overhead, we design a grant-free random access scheme based on joint active device detection and channel estimation (JADCE) for mmW/THz wideband massive access. In particular, by exploiting the simultaneously sparse and low-rank structure of mmW/THz channels with spreads in the delay-angular domain, we propose two multi-rank aware JADCE algorithms via applying the quotient geometry of product of complex rank-$L$ matrices with the number of clusters $L$. It is proved that the proposed algorithms require a smaller number of measurements than the currently known bounds on measurements of conventional simultaneously sparse and low-rank recovery algorithms. Statistical analysis also shows that the proposed algorithms can linearly converge to the ground truth with low computational complexity. Finally, extensive simulation results confirm the superiority of the proposed algorithms in terms of the accuracy of both activity detection and channel estimation.

cs.IT↗

arXiv2021

An Attention-Aided Deep Learning Framework for Massive MIMO Channel Estimation

Channel estimation is one of the key issues in practical massive multiple-input multiple-output (MIMO) systems. Compared with conventional estimation algorithms, deep learning (DL) based ones have exhibited great potential in terms of performance and complexity. In this paper, an attention mechanism, exploiting the channel distribution characteristics, is proposed to improve the estimation accuracy of highly separable channels with narrow angular spread by realizing the "divide-and-conquer" policy. Specifically, we introduce a novel attention-aided DL channel estimation framework for conventional massive MIMO systems and devise an embedding method to effectively integrate the attention mechanism into the fully connected neural network for the hybrid analog-digital (HAD) architecture. Simulation results show that in both scenarios, the channel estimation performance is significantly improved with the aid of attention at the cost of small complexity overhead. Furthermore, strong robustness under different system and channel parameters can be achieved by the proposed approach, which further strengthens its practical value. We also investigate the distributions of learned attention maps to reveal the role of attention, which endows the proposed approach with a certain degree of interpretability.

cs.IT↗

arXiv2021

Wireless Powered Communication Networks with Non-Ideal Circuit Power Consumption

Assuming non-ideal circuit power consumption at the energy harvesting (EH) nodes, we propose two practical protocols that optimize the performance of the harvest-then-transmit wireless powered communication networks (WPCNs) under two different objectives: (1) proportional fair (PF) resource allocation, and (2) sum rate maximization. These objectives lead to optimal allocations for the transmit power by the base station (BS), which broadcasts RF radiation over the downlink, and optimal durations of the EH phase and the uplink information transmission phases within the dynamic time-division multiple access (TDMA) frame. Compared to the max-sum-rate protocol, the PF protocol attains a higher level of system fairness at the expense of the sum rate degradation. The PF protocol is advantageous over the max-sum-rate protocol in terms of system fairness regardless of the circuit power consumption, whereas the uplink sum rates of both protocols converge when this power consumption increases.

cs.IT↗

arXiv2021

Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling

The popular federated edge learning (FEEL) framework allows privacy-preserving collaborative model training via frequent learning-updates exchange between edge devices and server. Due to the constrained bandwidth, only a subset of devices can upload their updates at each communication round. This has led to an active research area in FEEL studying the optimal device scheduling policy for minimizing communication time. However, owing to the difficulty in quantifying the exact communication time, prior work in this area can only tackle the problem partially by considering either the communication rounds or per-round latency, while the total communication time is determined by both metrics. To close this gap, we make the first attempt in this paper to formulate and solve the communication time minimization problem. We first derive a tight bound to approximate the communication time through cross-disciplinary effort involving both learning theory for convergence analysis and communication theory for per-round latency analysis. Building on the analytical result, an optimized probabilistic scheduling policy is derived in closed-form by solving the approximate communication time minimization problem. It is found that the optimized policy gradually turns its priority from suppressing the remaining communication rounds to reducing per-round latency as the training process evolves. The effectiveness of the proposed scheme is demonstrated via a use case on collaborative 3D objective detection in autonomous driving.

cs.NI↗

arXiv2021

Probabilistic Accumulate-then-Transmit in Wireless-Powered Covert Communications

In this paper, we investigate the optimal design of a wireless-powered covert communication (WP-CC) system, in which a probabilistic accumulate-then-transmit (ATT) protocol is proposed to maximize the communication covertness subject to a quality-of-service (QoS) requirement on communication. Specifically, in the considered WP-CC system, a full-duplex (FD) receiver transmits artificial noise (AN) to simultaneously charge an energy-constrained transmitter and to confuse a warden's detection on the transmitter's communication activity. With the probabilistic ATT protocol, the transmitter sends its information with a prior probability, i.e., $p$, conditioned on the available energy being sufficient. Our analysis shows that the probabilistic ATT protocol can achieve higher covertness than the traditional ATT protocol with $p=1$. In order to facilitate the optimal design of the WP-CC system, we also derive the warden's minimum detection error probability and characterize the effective covert rate from the transmitter to the receiver to quantify the communication covertness and quality, respectively. The derived analytical results facilitate the joint optimization of the probability $p$ and the information transmit power. We further present the optimal design of a cable-powered covert communication (CP-CC) system as a benchmark for comparison. Our simulation shows that the proposed probabilistic ATT protocol (with a varying $p$) can achieve the covertness upper bound determined by the CP-CC system, while the traditional ATT protocol (with $p=1$) cannot, which again confirms the benefits brought by the proposed probabilistic ATT in covert communications.

cs.IT↗

arXiv2021

Fronthaul Compression and Passive Beamforming Design for Intelligent Reflecting Surface-aided Cloud Radio Access Networks

This letter studies a cloud radio access network (C-RAN) with multiple intelligent reflecting surfaces (IRS) deployed between users and remote radio heads (RRH). Specifically, we consider the uplink transmission where each RRH quantizes the received signals from the users by either point-to-point compression or Wyner-Ziv compression and then transmits the quantization bits to the BBU pool through capacity limited fronthhual links. To maximize the uplink sum rate, we jointly optimize the passive beamformers of IRSs and the quantization noise covariance matrices of fronthoul compression. An joint fronthaul compression and passive beamforming design is proposed by exploiting the Arimoto-Blahut algorithm and semidefinte relaxation (SDR). Numerical results show the performance gain achieved by the proposed algorithm.

eess.SP↗

arXiv2021

Angle-Domain Intelligent Reflecting Surface Systems: Design and Analysis

This paper considers an angle-domain intelligent reflecting surface (IRS) system. We derive maximum likelihood (ML) estimators for the effective angles from the base station (BS) to the user and the effective angles of propagation from the IRS to the user. It is demonstrated that the accuracy of the estimated angles improves with the number of BS antennas. Also, deploying the IRS closer to the BS increases the accuracy of the estimated angle from the IRS to the user. Then, based on the estimated angles, we propose a joint optimization of BS beamforming and IRS beamforming, which achieves similar performance to two benchmark algorithms based on full CSI and the multiple signal classification (MUSIC) method respectively. Simulation results show that the optimized BS beam becomes more focused towards the IRS direction as the number of reflecting elements increases. Furthermore, we derive a closed-form approximation, upper bound and lower bound for the achievable rate. The analytical findings indicate that the achievable rate can be improved by increasing the number of BS antennas or reflecting elements. Specifically, the BS-user link and the BS-IRS-user link can obtain power gains of order $N$ and $NM^2$, respectively, where $N$ is the antenna number and $M$ is the number of reflecting elements.

cs.IT↗

arXiv2020

Feature-Aided Adaptive-Tuning Deep Learning for Massive Device Detection

With the increasing development of Internet of Things (IoT), the upcoming sixth-generation (6G) wireless network is required to support grant-free random access of a massive number of sporadic traffic devices. In particular, at the beginning of each time slot, the base station (BS) performs joint activity detection and channel estimation (JADCE) based on the received pilot sequences sent from active devices. Due to the deployment of a large-scale antenna array and the existence of a massive number of IoT devices, conventional JADCE approaches usually have high computational complexity and need long pilot sequences. To solve these challenges, this paper proposes a novel deep learning framework for JADCE in 6G wireless networks, which contains a dimension reduction module, a deep learning network module, an active device detection module, and a channel estimation module. Then, prior-feature learning followed by an adaptive-tuning strategy is proposed, where an inner network composed of the Expectation-maximization (EM) and back-propagation is introduced to jointly tune the precision and learn the distribution parameters of the device state matrix. Finally, by designing the inner layer-by-layer and outer layer-by-layer training method, a feature-aided adaptive-tuning deep learning network is built. Both theoretical analysis and simulation results confirm that the proposed deep learning framework has low computational complexity and needs short pilot sequences in practical scenarios.

cs.IT↗

arXiv2020

Ordinary Differential Equation-based CNN for Channel Extrapolation over RIS-assisted Communication

The reconfigurable intelligent surface (RIS) is considered as a promising new technology for reconfiguring wireless communication environments. To acquire the channel information accurately and efficiently, we only turn on a fraction of all the RIS elements, formulate a sub-sampled RIS channel, and design a deep learning based scheme to extrapolate the full channel information from the partial one. Specifically, inspired by the ordinary differential equation (ODE), we set up connections between different data layers in a convolutional neural network (CNN) and improve its structure. Simulation results are provided to demonstrate that our proposed ODE-based CNN structure can achieve faster convergence speed and better solution than the cascaded CNN.

cs.IT↗

arXiv2020

Cooperative Activity Detection: Sourced and Unsourced Massive Random Access Paradigms

This paper investigates the issue of cooperative activity detection for grant-free random access in the sixth-generation (6G) cell-free wireless networks with sourced and unsourced paradigms. First, we propose a cooperative framework for solving the problem of device activity detection in sourced random access. In particular, multiple access points (APs) cooperatively detect the device activity via exchanging low-dimensional intermediate information with their neighbors. This is enabled by the proposed covariance-based algorithm via exploiting both the sparsity-promoting and similarity-promoting terms of the device state vectors among neighboring APs. A decentralized approximate separating approach is introduced based on the forward-backward splitting strategy for addressing the formulated problem. Then, the proposed activity detection algorithm is adopted as a decoder of cooperative unsourced random access, where the multiple APs cooperatively detect the list of transmitted messages regardless of the identity of the transmitting devices. Finally, we provide sufficient conditions on the step sizes that ensure the convergence of the proposed algorithm in the sense of Bregman divergence. Simulation results show that the proposed algorithm is efficient for addressing both sourced and unsourced massive random access problems, while requires a shorter signature sequence and accommodates a significantly larger number of active devices with a reasonable antenna array size, compared with the state-of-art algorithms.

cs.IT↗

arXiv2020

Integrated Sensing, Computation and Communication in B5G Cellular Internet of Things

In this paper, we investigate the issue of integrated sensing, computation and communication (SCC) in beyond fifth-generation (B5G) cellular internet of things (IoT) networks. According to the characteristics of B5G cellular IoT, a comprehensive design framework integrating SCC is put forward for massive IoT. For sensing, highly accurate sensed information at IoT devices are sent to the base station (BS) by using non-orthogonal communication over wireless multiple access channels. Meanwhile, for computation, a novel technique, namely over-the-air computation (AirComp), is adopted to substantially reduce the latency of massive data aggregation via exploiting the superposition property of wireless multiple access channels. To coordinate the co-channel interference for enhancing the overall performance of B5G cellular IoT integrating SCC, two joint beamforming design algorithms are proposed from the perspectives of the computation error minimization and the weighted sum-rate maximization, respectively. Finally, extensive simulation results validate the effectiveness of the proposed algorithms for B5G cellular IoT over the baseline ones.

cs.IT↗