Local Channel State Information Research Articles

SCANet: A lightweight deep learning network for massive MIMO CSI feedback based on spatial and channel attention mechanism

Multi-user massive multiple-input multiple-output (MIMO) communication systems consume too much downlink bandwidth due to the huge channel state information (CSI) feedback, deep learning-based CSI feedback approaches fortunately can alleviate the feedback overhead while obtaining an accurate CSI. However, there is a trade-off between the high feedback performance and low computational complexity. In this paper, a low-complexity CSI feedback approach is proposed based on spatial and channel attention mechanism, namely the Spatial and Channel Attention Network (SCANet). Specifically, the spatial and channel attention mechanism makes the network’s attention mainly focus on the specific spatial regions and key feature channels. We devise a serial architecture in the encoder that composes of Spatial and Channel Attention Block (SCAB) and Encoder Transformer Block. Moreover, we design a hybrid architecture in the decoder that composes of the CNNs Block and Decoder Transformer Block. These designs enable the network to effectively extract both global and local CSI features. Computer simulations in both the indoor and outdoor scenarios show that under the same system configurations, the proposed low-complexity SCANet achieves almost the same performance as the state-of-the-art network while reducing the computational complexity by 85.76% fewer floating-point operations per second (FLOPS) on average.

Algorithm Design and Convergence Analysis for Coexistence of Cognitive Radio Networks in Unlicensed Spectrum.

This paper focuses on achieving the low-cost coexistence of the networks in an unlicensed spectrum by making them operate on non-overlapping channels. For achieving this goal, we first give a universal convergence analysis framework for the unlicensed spectrum allocation algorithm. Then, a one-timescale iteration-adjustable unlicensed spectrum allocation algorithm is developed, where the step size and timescale parameter can be jointly adjusted based on the system performance requirement and signal overhead concern. After that, we derive the sufficient condition for the one-timescale algorithm. Furthermore, the upper bound of convergence error of the one-timescale spectrum allocation algorithm is obtained. Due to the multi-timescale evolution of the network states in the wireless network, we further propose a two-timescale iteration-adjustable joint frequency selection and frequency allocation algorithm, where the frequency selection iteration timescale is set according to the slow-changing statistical channel state information (CSI), whereas the frequency allocation iteration timescale is set according to the fast-changing local CSI. Then, we derive the convergence condition of two-timescale algorithms and the upper bound of the corresponding convergence error. The experimentalresults show that the small timescale adjustment parameter and large step size can help decrease the convergence error. Moreover, compared with traditional algorithms, the two-timescale policy can achieve throughput similar to traditional algorithms with very low iteration overhead.

Distributed Unsupervised Learning for Interference Management in Integrated Sensing and Communication Systems

Nowadays, the multi-access interference problem in the ISAC systems can not be ignored. The study on interference management in ISAC has been envisioned as one of key technologies to support ubiquitous sensing functions. Different from the current work, a communications-sensing-intelligence converged network architecture is proposed to coordinate interference in this paper. Each base station equips with the individual deep neural networks to allocate power and beamforming. On this basis, the interference management is transformed into a functional optimization with stochastic constraints. An unsupervised learning algorithm is proposed to allocate power for interference management. Furthermore, a transfer learning method is presented to obtain the interference management in terms of transmit beamforming. Finally, the distributed management is obtained from the local channel state information in the multi-cell scenario. Simulation results verify the effectiveness of the proposed unsupervised learning interference management method in the ISAC systems.

Sequential Offloading for Distributed DNN Computation in Multiuser MEC Systems

This paper studies a sequential task offloading problem for a multiuser mobile edge computing (MEC) system. While most of the existing works consider static one-shot offloading optimization with fixed wireless channel conditions and fixed computational tasks, we consider a dynamic optimization approach, which embraces wireless channel fluctuations and random deep neural network (DNN) task arrivals over an infinite horizon. Specifically, we introduce a local CPU workload queue (WD-QSI) and an MEC server workload queue (MEC-QSI) to model the dynamic workload of DNN tasks at each WD and the MEC server, respectively. The transmit power and the partitioning of the local DNN task at each WD are dynamically determined based on the instantaneous channel conditions (to capture the transmission opportunities) and the instantaneous WD-QSI and MEC-QSI (to capture the dynamic urgency of the tasks) to minimize the average latency of the DNN tasks. The joint optimization can be formulated as an ergodic Markov decision process (MDP), in which the optimality condition is characterized by a centralized Bellman equation. However, the brute force solution of the MDP is not viable due to the curse of dimensionality as well as the requirement for knowledge of the global state information. To overcome these issues, we first decompose the MDP into multiple lower dimensional sub-MDPs, each of which can be associated with a WD or the MEC server. Next, we further develop a parametric online Q-learning algorithm, so that each sub-MDP is solved locally at its associated WD or the MEC server. The proposed solution is completely decentralized in the sense that the transmit power for sequential offloading and the DNN task partitioning can be determined based on the local channel state information (CSI) and the local WD-QSI at the WD only. Additionally, no prior knowledge of the distribution of the DNN task arrivals or the channel statistics will be needed for the MEC server. The proposed solution can achieve the superb performance over various state-of-the-art baselines.

Beamforming Design for In-Band Full-Duplex Multi-Cell Multi-User MIMO Networks With Global and Local CSI

This paper investigates beamforming techniques for in-band full-duplex multi-cell multi-user (IBFD-MCMU) wireless networks considering hardware impairments (HWIs), channel uncertainty, and limited channel state information (CSI). For the global CSI scenario, we first enhance zero-forcing (ZF), maximum ratio transmission and combining (MRTC), and minimum mean-squared error (MMSE) beamforming to be compatible with multi-antenna users and IBFD base stations. Then, we investigate beamforming schemes for the local CSI assumption where only intra-cell channel knowledge is fully available at the base stations, and inter-cell channels are known statistically due to the limited training resources. With these limitations, two MMSE-based methods are proposed, which regard unknown CSI as random instances (i.e., eMMSE-RI) and noise (i.e., eMMSE-N). We explore the self-interference cancellation (SIC) capability of beamformers and evaluate the performance of these methods in 3GPP scenarios. Numerical results reveal that the enhanced MMSE beamforming can achieve the desired IBFD with low analog SIC depth, inspiring a low-cost IBFD transceiver design. The practical imperfections (e.g., transceiver HWIs, channel uncertainty, limited CSI) decrease the achievable sum rate but do not reduce the IBFD gain. With CSI limitations, eMMSE-RI outperforms eMMSE-N for microcells, where the probability of the presence of LOS is high, whereas eMMSE-N performs better when cell size is enlarged.

Online Learning for Joint Energy Harvesting and Information Decoding Optimization in IoT-Enabled Smart City

In this study, we first present a framework that jointly optimize energy harvesting and information decoding for Internet of Things (IoT) devices, which are capable of simultaneous wireless information and power reception, in a smarty city. In particular, a generalized power splitting receiver for IoT devices is designed, where each antenna in the receiver has an independent power splitter, unlike the existing works in which only one power splitter is employed regardless of the number of antennas in the receiver. Such a receiver design can provide a great degree of freedom to improve the network performance. Based on the presented framework, for each IoT device, we formulate an optimization problem whose objective is to maximize the harvested energy of each IoT device while satisfying its data rate requirement. To solve this problem, we propose a double-deep deterministic policy gradient based online learning algorithm which enables each IoT device to jointly determine receive beamforming and power splitting ratio vectors in real-time. Further, each IoT device can implement the proposed algorithm in a distributed manner using only its local channel state information. As such, cooperation and information exchange among the base stations and IoT devices are not necessary when performing the proposed algorithm at IoT devices. The extensive simulation results show the validity of the proposed algorithm.

Cooperative Beamforming With Nonlinear Power Amplifiers: A Deep Learning Approach for Distributed Networks

Network densification is essential to enhance the areal capacity of future wireless networks, for which the user-centric network is a promising solution. In the perspective of network scalability, user association and cooperative beamforming (BF) among the base stations (BSs) should be designed elaborately to manage strong interference from nearby BSs. However, practical systems with hardware impairments including nonlinearity of power amplifiers may disturb these techniques and make the network difficult to be scalable. The nonlinearity of power amplifiers affects not only radio frequency (RF)-level signal but also performance according to the number of user equipments (UEs), resulting in necessity of re-designing network-level operations including BS-UE association. This paper proposes a deep learning-based cooperative BF framework for distributed networks with nonlinear power amplifiers. To optimize the cooperative BF for complicated nonlinear systems, we adopt unsupervised learning approach with constraints. To reduce the communication overhead of the network, we propose a novel neural network structure, from which the BSs can perform the cooperative BF in distributed manner. In particular, the information exchange between the central unit and the local BSs is reduced by designing neural network so that the local channel state information are utilized only in the local BSs while the central unit utilizes only covariance matrices. We show that the proposed scheme achieves a higher effective sum rate compared to the baseline schemes by adjusting the user association, BF, and power allocation to control interference and nonlinear distortion with reduced communication overhead.

AI Service Placement for Multi-Access Edge Intelligence Systems in 6G

This paper studies the artificial intelligent (AI) task deployment problem of a multi-access edge intelligent system in a 6G network, in which the cloud server broadcasts the AI program to the edge computing nodes. In particular, task nodes can perform remote processing by offloading AI tasks to cloud servers or other edge computing nodes, or they can perform processing tasks locally. In order to minimize the total computing time and energy consumption of all task nodes and maximize the inference accuracy of AI tasks, we jointly optimize the resource allocation and computing offloading decision of each node by solving a mixed-integer non-linear programming (MINLP) problem. In order to efficiently solve this non-convex problem, we propose an alternating direction multiplier method (ADMM) based algorithm, which effectively decomposes the problem into easy-to-handle MINLP subproblems. Through the proposed ADMM-based algorithm, each task node can use local channel state information (CSI) to optimize its calculation mode and resource allocation, which is more suitable for large-scale networks. The simulation results show that this method is significantly better than other benchmarks in various network environments, and the computational complexity is relatively low.

Distributed Design of Wireless Powered Fog Computing Networks With Binary Computation Offloading

This paper investigates a multi-user wireless powered fog computing (FC) network, where multiple energy-limited wireless sensor devices (WSDs) first harvest energy from a nearby hybrid access point (HAP), and then compute their tasks locally (i.e., the local computing (LC) mode) or offload the tasks to the HAP (i.e., the FC mode) via a binary offloading policy. In order to pursue the green computing network design, an optimization problem is formulated to minimize the transmit power at the HAP by jointly optimizing the time allocation ratio and the computing mode selection vector, under the energy causality constraints and the WSDs’ computing rate requirements constraints. To efficiently solve the formulated non-convex problem in a distributed manner, it is first transformed into an approximate form, and then an alternating direction method of multipliers (ADMM)-based algorithm is designed to solve the transformed problem, based on which the successive convex approximation (SCA) is adopted to improve the approximating precision in an iterative way. With the proposed ADMM-based distributed algorithm, each WSD is able to optimize its computing mode and offloading time with local channel state information (CSI), which thus is more suitable for large-scale networks. For comparison, a channel-sorting-based (CSB) centralized algorithm with global CSI is also presented, and the computational complexities of the proposed ADMM-based algorithm and the CSB algorithm are analyzed. Simulation results show that the proposed distributed algorithm achieves a comparable performance with the CSB centralized algorithm and the exhaustive search method. It is also observed that to minimize the transmit power at the HAP, the WSDs with the better channel quality are inclined to select the LC mode, which is much different from traditional sum-computation-rate maximization design.

Cooperative space-time line code for relay-assisted internet of things

We propose a novel cooperative space–time line code (C-STLC) scheme to improve performance of a relay-assisted internet of things (R-IoT). The proposed C-STLC operates with fully distributed manner, where each relay IoT device (RID) attempts to decode the received signal from a source IoT device at the first hop and the RIDs, that succeeded decoding, send the STLC encoded signal based on their local channel state information (CSI) to a single access point (AP) at the second hop. Then, the AP decodes the received signals without CSI. As a main result, we mathematically analyze the outage probability (OP) of the proposed C-STLC scheme. It is shown that the proposed C-STLC significantly outperforms conventional cooperative relaying techniques in terms of the OP.

Coordinated Sum-Rate Maximization in Multicell MU-MIMO With Deep Unrolling

Coordinated weighted sum-rate maximization in multicell MIMO networks with intra- and intercell interference and local channel state at the base stations is recognized as an important yet difficult problem. A classical, locally optimal solution is obtained by the weighted minimum mean squared error (WMMSE) algorithm which facilitates a distributed implementation in multicell networks. However, it often suffers from slow convergence and therefore large communication overhead. To obtain more practical solutions, the unrolling/unfolding of traditional iterative algorithms gained significant attention. In this work, we demonstrate a complete unfolding of the WMMSE algorithm for transceiver design in multicell MU-MIMO interference channels with local channel state information. The resulting architecture termed GCN-WMMSE applies ideas from graph signal processing and is agnostic to different wireless network topologies, while exhibiting a low number of trainable parameters and high efficiency w.r.t. training data. It significantly reduces the number of required iterations while achieving performance similar to the WMMSE algorithm, alleviating the overhead in a distributed deployment. Additionally, we review previous architectures based on unrolling the WMMSE algorithm and compare them to GCN-WMMSE in their specific applicable domains.

Radio Resource Management for C-V2X: From a Hybrid Centralized-Distributed Scheme to a Distributed Scheme

Spectrum sharing in cellular vehicle-to-everything (C-V2X) has been conceived as a promising solution to improve spectrum efficiency. However, the co-channel interference incurred with it may cause severe performance degradation to vehicular links. Thereby, radio resource management (RRM) is motivated and designed to ensure communication reliability and increase system capacity. One challenge is that RRM involves channel allocation and power control, which are tightly coupled and hard to optimize simultaneously. Another challenge for this is the difficulty adapting centralized RRM schemes, requiring global channel state information (CSI) and causing high signaling overhead. To tackle these challenges, we propose the hybrid centralized-distributed RRM scheme and the distributed RRM scheme. Specifically, we prove a decoupling method that provides a theoretical lower bound so that channel allocation and power control can be optimized independently. Given the decoupling method, the hybrid centralized-distributed RRM scheme is based on graph matching and reinforcement learning (GMRL) to maximize system capacity and guarantee reliability requirements. Further, to decrease computation complexity and signaling overhead, the distributed RRM scheme that only requires local CSI with hybrid-framework reinforcement learning (HFRL) is exploited. Finally, both schemes are numerically evaluated through experiments and outperform other deep Q-network (DQN)-based schemes.

A QoS-Adaptive Interference Alignment Technique for In-Band Full-Duplex Multi-Antenna Cellular Networks

In this paper, we propose a novel interference alignment (IA) technique for an in-band full-duplex (IBFD) multiple-input multiple-output (MIMO) cellular network where a base station (BS) and user equipment (UE) are equipped with multiple antennas, and the local channel state information (CSI) is available at all nodes. Considering a practical IBFD MIMO cellular network, it is assumed that only the BS operates with full-duplex (FD) communication while UE operate in half-duplex (HD) mode. These IBFD networks introduce a new type of interference called cross-link interference (CLI), in which uplink UE affects downlink UE. The proposed IA technique consists of two symmetric IA schemes according to the number of antennas in the uplink and downlink UE, and both schemes effectively mitigate CLI in the IBFD MIMO network. It is worth noting that both IA schemes are adaptively applicable according to the network's quality-of-service (QoS) requirements, such as uplink and downlink traffic demands. Furthermore, we theoretically characterize and prove the achievable sum-degrees-of-freedom (DoF) of the proposed IA technique. Simulation results show that the proposed IA technique significantly improves the sum rate performance compared to conventional HD communications (multi-user MIMO) while achieving the same achievable DoF as the interference-free IBFD MIMO network.

Decision fusion for multi-route and multi-hop Wireless Sensor Networks over the Binary Symmetric Channel

The decision fusion for multi-route and multi-hop Wireless Sensor Networks (WSNs) is studied, wherein a discrete memoryless channel model, i.e., the Binary Symmetric Channel (BSC), is considered to characterize the relay transmission of each hop from the local sensor to the fusion center. In particular, we first develop the optimal log-likelihood ratio (LLR) based decision fusion rule, wherein the fusion center is assumed to have perfect knowledge of both the local sensor performance indices and the Channel State Information (CSI), i.e., crossover probability for each BSC. Secondly, we derive the suboptimum and robust fusion rules for two cases. In the first case, channel condition from the source to the local sensor is considered to be ideal. In the second case, the crossover probability for each BSC is assumed to be relatively large or small. Our result show that our suboptimum fusion detectors require less or no a priori information about crossover probability and/or the local sensor performance indices, and thus are easy to implement. We also show that the simple decision fusion statistic, i.e., the counting-based statistic, can be directly derived from the optimal LLR-based statistic for both cases. These suboptimum fusion rules are clearly desired for applications, wherein perfect estimation of the local sensor performance and CSI is complexity-intensive or unachievable. Furthermore, the optimal LLR-based scheme for joint decision fusion and CSI estimation is proposed. We uniformly quantize the equivalent crossover probability into discrete status, and thus give a suboptimum but more computationally practical scheme. The performance evaluation is finally developed both analytically and through simulation.

Uplink Performance of Cell-Free Massive MIMO With Multi-Antenna Users Over Jointly-Correlated Rayleigh Fading Channels

In this paper, we investigate a cell-free massive MIMO system with both access points (APs) and user equipments (UEs) equipped with multiple antennas over jointly-correlated Rayleigh fading channels. We study four uplink implementations, from fully centralized processing to fully distributed processing, and derive their achievable spectral efficiency (SE) expressions with minimum mean-squared error successive interference cancellation (MMSE-SIC) detectors and arbitrary combining schemes. Furthermore, the global and local MMSE combining schemes are derived based on full and local channel state information (CSI) obtained under pilot contamination, which can maximize the achievable SE for the fully centralized and distributed implementation, respectively. We study a two-layer decoding implementation with an arbitrary combining scheme in the first layer and optimal large-scale fading decoding (LSFD) in the second layer. Besides, we compute novel closed-form SE expressions for the two-layer decoding implementation with maximum ratio (MR) combining. In the numerical results, we compare the SE performance for different implementation levels, combining schemes, and channel models. It is important to note that increasing the number of antennas per UE may degrade the SE performance.

Scalable User Rate and Energy-Efficiency Optimization in Cell-Free Massive MIMO

This paper considers a cell-free massive multiple-input multiple-output network (cfm-MIMO) with a massive number of access points (APs) distributed across an area to deliver information to multiple users. Based on only local channel state information, conjugate beamforming is used under both proper and improper Gaussian signalings. To accomplish the mission of cfm-MIMO in providing fair service to all users, the problem of power allocation to maximize the geometric mean (GM) of users’ rates (GM-rate) is considered. A new scalable algorithm, which iterates linear-complex closed-form expressions and thus is practical regardless of the scale of the network, is developed for its solution. The problem of quality-of-service (QoS) aware network energy-efficiency is also addressed via maximizing the ratio of the GM-rate and the total power consumption, which is also addressed by iterating linear-complex closed-form expressions. Intensive simulations are provided to demonstrate the ability of the GM-rate based optimization to achieve multiple targets such as a uniform QoS, a good sum rate, and a fair power allocation to the APs.

Hybrid Beamforming and Adaptive RF Chain Activation for Uplink Cell-Free Millimeter-Wave Massive MIMO Systems

In this work, we investigate hybrid analog–digital beamforming (HBF) architectures for uplink cell-free (CF) millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems. We first propose two HBF schemes, namely, decentralized HBF (D-HBF) and semi-centralized HBF (SC-HBF). In the former, both the digital and analog beamformers are generated independently at each AP based on the local channel state information (CSI). In contrast, in the latter, only the digital beamformer is obtained locally at the access point (AP), whereas the analog beamforming matrix is generated at the central processing unit (CPU) based on the global CSI received from all APs. We show that the analog beamformers generated in these two HBF schemes provide approximately the same achievable rates despite the lower complexity of D-HBF and its lack of CSI requirement. Furthermore, to reduce the power consumption, we propose a novel adaptive radio frequency (RF) chain-activation (ARFA) scheme, which dynamically activates/deactivates RF chains and their connected analog-to-digital converters (ADCs) and phase shifters (PSs) at the APs based on the CSI. For the activation of RF chains, low-complexity algorithms are proposed, which can achieve significant improvement in energy efficiency (EE) with only a marginal loss in the total achievable rate.

Team MMSE Precoding With Applications to Cell-Free Massive MIMO

This article studies a novel distributed precoding design, coined <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">team minimum mean-square error</i> (TMMSE) precoding, which rigorously generalizes classical centralized MMSE precoding to distributed operations based on transmitter-specific channel state information (CSIT). Building on the so-called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">theory of teams</i> , we derive a set of necessary and sufficient conditions for optimal TMMSE precoding, in the form of an infinite dimensional linear system of equations. These optimality conditions are further specialized to cell-free massive MIMO networks, and explicitly solved for two important examples, i.e., the classical case of local CSIT and the case of unidirectional CSIT sharing along a serial fronthaul. The latter case is relevant, e.g., for the recently proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">radio stripe</i> concept and the related advances on sequential processing exploiting serial connections. In both cases, our optimal design outperforms the heuristic methods that are known from the previous literature. Duality arguments and numerical simulations validate the effectiveness of the proposed team theoretical approach in terms of ergodic achievable rates under a sum-power constraint.

Deep Learning-Based Resource Allocation for Device-to-Device Communication

In this paper, a deep learning (DL) framework for the optimization of the resource allocation in multi-channel cellular systems with device-to-device (D2D) communication is proposed. Thereby, the channel assignment and discrete transmit power levels of the D2D users, which are both integer variables, are optimized for maximization of the overall spectral efficiency whilst maintaining the quality-of-service (QoS) of the cellular users. Depending on the availability of channel state information (CSI), two different configurations are considered, namely 1) centralized operation with full CSI and 2) distributed operation with partial CSI, where in the latter case, the CSI is encoded according to the capacity of the feedback channel. Instead of solving the resulting resource allocation problem for each channel realization, a DL framework is proposed, where the optimal resource allocation strategy for arbitrary channel conditions is approximated by deep neural network (DNN) models. Furthermore, we propose a new training strategy that combines supervised and unsupervised learning methods and a local CSI sharing strategy to achieve near-optimal performance while enforcing the QoS constraints of the cellular users and efficiently handling the integer optimization variables based on a few ground-truth labels. Our simulation results confirm that near-optimal performance can be attained with low computation time, which underlines the real-time capability of the proposed scheme. Moreover, our results show that not only the resource allocation strategy but also the CSI encoding strategy can be efficiently determined using a DNN. Furthermore, we show that the proposed DL framework can be easily extended to communication systems with different design objectives.

Coordinated beamforming, interference-aware power control, and scheduling framework for 6G wireless networks

In this study, we propose a novel sum-rate enhancement framework for future 6G multi-cell multiple-input multiple-output (MIMO) uplink networks, which exploits the coordinated beamforming, power control, and user scheduling (CBPS) technique. The proposed CBPS technique not only significantly mitigates the inter-cell interference in transmit beamforming for users but also eliminates the intra-cell interference among the users in the same cell the receive beamforming at base stations (BSs). Additionally, we propose a user scheduling algorithm that selects the users whose effective channel vectors are mutually orthogonal to each other to increase the spectral efficiency and an interference-aware power control technique for users to further reduce inter-cell interference. It is worth noting that the proposed CBPS framework does not require information exchange among the BSs and operates in a non-iterative and distributed manner based on local channel state information (CSI) at both the BSs and users. Thus, it can be implemented for practical wireless systems with low complexity. Extensive simulation results show that the proposed CBPS framework significantly outperforms conventional techniques in multi-cell environments.