No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Towards 6G: Deep Learning in Cell-Free Massive MIMO
... Moreover, MU-MIMO also failed to tackle the inter-cell interference issues despite appreciable average cell throughput gains. Hence, cell-free massive MIMO (CF-mMIMO) has emerged as a potential sixth-generation (6G) technology [1], [2] that incorporates the benefits of a distributed system and massive MIMO, while avoiding excessive inter-cell handover, diminishing the detrimental shading effect and handling the control signaling interference [3]. In CF-mMIMO, there exist no cell boundaries and access points (APs) are dispersed throughout a given geographic area and connected to a central processing unit (CPU) through fronthaul links for jointly serving the user equipments (UEs) [4], [5]. ...
... Due to the time-selective fading, the AP uses a pilot signal [35] to estimate the channel coefficientsĝ d mk over first signaling period of each transmitted block asĝ d mk (1). As a result,ĝ d mk for z th signaling position is expanded as followŝ ...
p>One of the candidate technologies for sixth-generation (6G) wireless communication systems is cell-free massive multiple-input multiple-output (CF-mMIMO) communication, which can control inter-cell interference in MIMO systems. This paper investigates the performance of a full-duplex (FD) CF-mMIMO system with practical limited-capacity fronthaul links. The proposed system employs a large number $M$ distributed FD access points (APs), arbitrarily distributed $K_d$ downlink (DL) and $K_u$ uplink (UL) half-duplex (HD) single-antenna user equipments (UEs), and a central processing unit (CPU). To exploit energy efficiency (EE) and potential throughput gains of FD systems, each AP is linked to the CPU by a fronthaul link with limited capacity that handles the quantized UL/DL data to and from the CPU. On the same spectrum resource, each AP is expected to support $K$ single-antenna HD UEs, where $K = (K_u + K_d)$. Despite having a minimal signal processing complexity, our approach offers a uniform quality of service (QoS) to all UEs while providing improved spectrum efficiency and EE. Imperfect channel state information and mobility of the UEs are also considered. Closed-form expression for the outage probability is derived using the optimal uniform quantization and maximum-ratio combining/maximum-ratio transmission considering the Welch-Satterthwaite approximation. Additionally, the asymptotic and infinite-$M$ outage performance of the proposed system are analytically studied and verified via Monte-Carlo simulation.</p
... Moreover, MU-MIMO also failed to tackle the inter-cell interference issues despite appreciable average cell throughput gains. Hence, cell-free massive MIMO (CF-mMIMO) has emerged as a potential sixth-generation (6G) technology [1], [2] that incorporates the benefits of a distributed system and massive MIMO, while avoiding excessive inter-cell handover, diminishing the detrimental shading effect and handling the control signaling interference [3]. In CF-mMIMO, there exist no cell boundaries and access points (APs) are dispersed throughout a given geographic area and connected to a central processing unit (CPU) through fronthaul links for jointly serving the user equipments (UEs) [4], [5]. ...
... Due to the time-selective fading, the AP uses a pilot signal [35] to estimate the channel coefficientsĝ d mk over first signaling period of each transmitted block asĝ d mk (1). As a result,ĝ d mk for z th signaling position is expanded as followŝ ...
p>One of the candidate technologies for sixth-generation (6G) wireless communication systems is cell-free massive multiple-input multiple-output (CF-mMIMO) communication, which can control inter-cell interference in MIMO systems. This paper investigates the performance of a full-duplex (FD) CF-mMIMO system with practical limited-capacity fronthaul links. The proposed system employs a large number $M$ distributed FD access points (APs), arbitrarily distributed $K_d$ downlink (DL) and $K_u$ uplink (UL) half-duplex (HD) single-antenna user equipments (UEs), and a central processing unit (CPU). To exploit energy efficiency (EE) and potential throughput gains of FD systems, each AP is linked to the CPU by a fronthaul link with limited capacity that handles the quantized UL/DL data to and from the CPU. On the same spectrum resource, each AP is expected to support $K$ single-antenna HD UEs, where $K = (K_u + K_d)$. Despite having a minimal signal processing complexity, our approach offers a uniform quality of service (QoS) to all UEs while providing improved spectrum efficiency and EE. Imperfect channel state information and mobility of the UEs are also considered. Closed-form expression for the outage probability is derived using the optimal uniform quantization and maximum-ratio combining/maximum-ratio transmission considering the Welch-Satterthwaite approximation. Additionally, the asymptotic and infinite-$M$ outage performance of the proposed system are analytically studied and verified via Monte-Carlo simulation.</p
The mobile data traffic has been exponentially growing during the last decades. This was enabled by the densification of the network infrastructure in terms of increased cell density (i.e., Ultra-Dense Network (UDN)) and/or increased number of active antennas per Access Point (AP) (i.e., massive Multiple-Input Multiple-Output (mMIMO)). However, neither UDN nor mMIMO will meet the increasing demand for the data rate of the Sixth Generation (6G) wireless communications due to the inter-cell interference and large quality-of-service variations. Cell-Free (CF) mMIMO, which combines the best aspects of UDN and mMIMO, is viewed as a key solution to this issue. In such systems, each User Equipment (UE) is served by a preferred set of surrounding APs cooperatively. In this paper, we provide a survey of the state-of-the-art literature on CF mMIMO. As a starting point, the significance and the basic properties of CF mMIMO are highlighted. We then present the canonical framework to discuss the essential details (i.e., transmission procedure and mathematical system model). Next, we provide a deep look at the resource allocation and signal processing problems related to CF mMIMO and survey the up-to-date schemes and algorithms. After that, we discuss the practical issues in implementing CF mMIMO and point out the potential future directions. Finally, we conclude this paper with a summary of the key lessons learned in this field.
In recent times, the rapid growth in mobile subscriptions and the associated demand for high data rates fuels the need for a robust wireless network design to meet the required capacity and coverage. Deploying massive numbers of cellular base stations (BSs) over a geographic area to fulfill high-capacity demands and broad network coverage is quite challenging due to inter-cell interference and significant rate variations. Cell-free massive MIMO (CF-mMIMO), a key enabler for 5G and 6G wireless networks, has been identified as an innovative technology to address this problem. In CF-mMIMO, many irregularly scattered single access points (APs) are linked to a central processing unit (CPU) via a backhaul network that coherently serves a limited number of mobile stations (MSs) to achieve high energy efficiency (EE) and spectral gains. This paper presents key areas of applications of CF-mMIMO in the ubiquitous 5G, and the envisioned 6G wireless networks. First, a foundational background on massive MIMO solutions-cellular massive MIMO, network MIMO, and CF-mMIMO is presented, focusing on the application areas and associated challenges. Additionally, CF-mMIMO architectures, design considerations, and system modeling are discussed extensively. Furthermore, the key areas of application of CF-mMIMO such as simultaneous wireless information and power transfer (SWIPT), channel hardening, hardware efficiency, power control, non-orthogonal multiple access (NOMA), spectral efficiency (SE), and EE are discussed exhaustively. Finally, the research directions, open issues, and lessons learned to stimulate cutting-edge research in this emerging domain of wireless communications are highlighted.
With the explosive growth of mobile communication technology, the number of access terminals has increased dramatically, which will make the pilot contamination caused by pilot reuse extremely worse due to limited pilot resources. It is difficult to apply a traditional pilot assignment algorithm to serve the numerous access terminals simultaneously in real time with low complexity, so there is necessity to design a scalable pilot assignment scheme in the case of massive access. In this paper, we propose a scalable deep learning-based pilot assignment algorithm to maximize the sum spectral efficiency (SE) of cell-free large-scale distributed multiple-input multiple-output (MIMO) systems with massive access. The mapping between user locations and pilot assignment schemes is learned by a deep neural network (DNN). The training samples of the DNN are generated by a min-max algorithm, which minimizes the maximum interference to alleviate pilot contamination. The output of the pretrained DNN is used as the initial value of the min-max algorithm to achieve better pilot assignment schemes and reduce the algorithm complexity. The simulation results show that the proposed algorithm has better convergence with massive access and achieves a higher sum SE in near real time.
Power allocation plays a central role in cell-free (CF) massive multiple-input multiple-output (MIMO) systems. Many effective methods, e.g., the weighted minimum mean square error (WMMSE) algorithm, have been developed for optimizing the power allocation. Since the state of the channels evolves in time, the power allocation should stay in tune with this state. The present methods to achieve this typically find a near-optimal solution in an iterative manner at the cost of a considerable computational complexity, potentially compromising the timeliness of the power allocation. In this paper we address this problem by exploring the use of data-driven methods since they can achieve near-optimal performance with a low computational complexity. Deep reinforcement learning (DRL) is one such method. We explore two DRL power allocation methods, namely the deep Q-network (DQN) and the deep deterministic policy gradient (DDPG). The objective is to maximize the sum-spectral efficiency (SE) in CF massive MIMO, operating in the microwave domain. The numerical results, obtained for a 3GPP indoor scenario, show that the DRL-based methods have a competitive performance compared with WMMSE and the computational complexity is much lower. We found that the well-trained DRL methods achieved at least a 33% higher sum-SE than the WMMSE algorithm. The execution times of the DRL methods in our simulation platform are 0.1% of the WMMSE algorithm.
A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN's applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work.
Wireless communications are envisioned to bring about dramatic changes in the future, with a variety of emerging applications, such as virtual reality (VR), Internet of Things (IoT), etc., becoming a reality. However, these compelling pplications have imposed many new challenges, including unknown channel models, low-latency requirement in large-scale superdense networks, etc. The amazing success of deep learning (DL) in various fields, particularly in computer science, has recently stimulated increasing interest in applying it to address those challenges. Hence, in this review, a pair of dominant methodologies of using DL for wireless communications are investigated. The first one is DL-based architecture design, which breaks the classical model-based block design rule of wireless communications in the past decades. The second one is DL-based algorithm design, which will be illustrated by several examples in a series of typical techniques conceived for 5G and beyond. Their principles, key features, and performance gains will be discussed. Furthermore, open problems and future research opportunities will also be pointed out, highlighting the interplay between DL and wireless communications. We expect that this review can stimulate more novel ideas and exciting contributions for intelligent wireless communications.
Massive multiple-input multiple-output (MIMO) is a key technology in 5G. It enables multiple users to be served in the same time-frequency block through precoding or beamforming techniques, thus increasing capacity, reliability and energy efficiency. A key issue in massive MIMO is the allocation of power to the individual antennas, in order to achieve a specific objective, e.g., the maximization of the minimum capacity guaranteed to each user. This is a nondeterministic polynomial (NP)-hard problem that needs to be solved in a timely manner since the state of the channels evolves in time and the power allocation should stay in tune with this state. Although several heuristics have been proposed to solve this problem, these entail a considerable time-complexity. As a result, with the present methods, it cannot be guaranteed that power allocation happens in time. To solve this problem, we propose a deep neural network (DNN). A DNN has a low time complexity, but requires an extensive, offline, training process before it becomes operational. The DNN we propose is the combination of two convolutional layers and four fully connected layers. It takes as input the long-term fading information and it outputs the power for each antenna element to each user. We limit ourselves to the case of time-division duplex (TDD) based sub-6GHz networks. Numerical results show that, our DNN-based method approximates very closely the results of a commonly used heuristic based on the bisection algorithm.
A cell-free massive multiple-input multiple-output (MIMO) uplink is considered, where quantize-and-forward (QF) refers to the case where both the channel estimates and the received signals are quantized at the access points (APs) and forwarded to a central processing unit (CPU) whereas in combine-quantize-and-forward (CQF), the APs send the quantized version of the combined signal to the CPU. To solve the non-convex sum rate maximization problem, a heuristic sub-optimal scheme is exploited to convert the power allocation problem into a standard geometric programme (GP). We exploit the knowledge of the channel statistics to design the power elements. Employing large-scale fading (LSF) with a deep convolutional neural network (DCNN) enables us to determine a mapping from the LSF coefficients and the optimal power through solving the sum rate maximization problem using the quantized channel. Four possible power control schemes are studied, which we refer to as i) small-scale fading (SSF)-based QF; ii) LSF-based CQF; iii) LSF use-and-then-forget (UatF)-based QF; and iv) LSF deep learning (DL)-based QF, according to where channel estimation is performed and exploited and how the optimization problem is solved. Numerical results show that for the same fronthaul rate, the throughput significantly increases thanks to the mapping obtained using DCNN.
The recently commercialized fifth-generation (5G) wireless networks have achieved many improvements, including air interface enhancement, spectrum expansion, and network intensification by several key technologies, such as massive multiple-input multiple-output (MIMO), millimeter-wave communications, and ultra-dense networking. Despite the deployment of 5G commercial systems, wireless communications is still facing many challenges to enable connected intelligence and a myriad of applications such as industrial Internet-of-things, autonomous systems, brain-computer interfaces, digital twin, tactile Internet, etc. Therefore, it is urgent to start research on the sixth-generation (6G) wireless communication systems. Among the candidate technologies for 6G, cell-free massive MIMO, which combines the advantages of distributed systems and massive MIMO, is a promising solution to enhance the wireless transmission efficiency and provide better coverage. In this paper, we present a comprehensive study on cell-free massive MIMO for 6G wireless communication networks with a special focus on the signal processing perspective. Specifically, we introduce enabling physical layer technologies for cell-free massive MIMO, such as user association, pilot assignment, transmitter, and receiver design, as well as power control and allocation. Furthermore, some current and future research problems are described.
Imagine a coverage area where each mobile device is communicating with a preferred set of wireless access points (among many) that are selected based on its needs and cooperate to jointly serve it, instead of creating autonomous cells. This effectively leads to a user-centric post-cellular network architecture, which can resolve many of the interference issues and service-quality variations that appear in cellular networks. This concept is called User-centric Cell-free Massive MIMO (multiple-input multiple-output) and has its roots in the intersection between three technology components: Massive MIMO, coordinated multipoint processing, and ultra-dense networks. The main challenge is to achieve the benefits of cell-free operation in a practically feasible way, with computational complexity and fronthaul requirements that are scalable to enable massively large networks with many mobile devices. This monograph covers the foundations of User-centric Cell-free Massive MIMO, starting from the motivation and mathematical definition. It continues by describing the state-of-the-art signal processing algorithms for channel estimation, uplink data reception, and downlink data transmission with either centralized or distributed implementation. The achievable spectral efficiency is mathematically derived and evaluated numerically using a running example that exposes the impact of various system parameters and algorithmic choices. The fundamental tradeoffs between communication performance, computational complexity, and fronthaul signaling requirements are thoroughly analyzed. Finally, the basic algorithms for pilot assignment, dynamic cooperation cluster formation, and power optimization are provided, while open problems related to these and other resource allocation problems are reviewed. All the numerical examples can be reproduced using the accompanying Matlab code.
This paper deals with the calibration of Time Division Duplexing (TDD) reciprocity in an Orthogonal Frequency Division Multiplexing (OFDM) based Cell Free Massive MIMO system where the responses of the (Radio Frequency) RF chains render the end to end channel non-reciprocal, even though the physical wireless channel is reciprocal. We further address the non-availability of the uplink channel estimates at locations other than pilot subcarriers and propose a single-shot solution to estimate the downlink channel at all subcarriers from the uplink channel at selected pilot subcarriers. We propose a cascade of two Deep Neural Networks (DNN) to achieve the objective. The proposed method is easily scalable and removes the need for relative reciprocity calibration based on the cooperation of antennas, which usually introduces dependency in Cell Free Massive MIMO systems.
The combination of cell-free massive multiple-input multiple-output (MIMO) systems along with millimeter-wave (mmWave) bands is indeed one of most promising technological enablers of the envisioned wireless Gbit/s experience. However, both massive antennas at access points and large bandwidth at mmWave induce high computational complexity to exploit an accurate estimation of channel state information. Considering the sparse mmwave channel matrix as a natural image, we propose a practical and accurate channel estimation framework based on the fast and flexible denoising convolutional neural network (FFDNet). In contrast to previous deep learning based channel estimation methods, FFDNet is suitable a wide range of signal-to-noise ratio levels with a flexible noise level map as the input. More specifically, we provide a comprehensive investigation to optimize the FFDNet based channel estimator. Extensive simulation results validate that the training speed of FFDnet is faster than state-of-the-art channel estimators without sacrificing normalized mean square error performance, which makes FFDNet as an practical channel estimator for cell-free mmWave massive MIMO systems.
Making MIMO truly “massive” involves liberating it from the shackles of form factor constraints, by allowing arbitrarily large groups of neighboring nodes to opportunistically form virtual antenna arrays for both transmission and reception. Moving such distributed MIMO (DMIMO) systems from the realm of information theory to practice requires synchronization of the cooperating nodes at multiple levels. We are interested in all-wireless systems which are severely constrained in the amount of information that can be exchanged among the cooperating nodes, in contrast to recent proposals in massive MIMO (co-located antennas) or base station cooperation (which relies on a high-speed wired backhaul). The goal of this paper is to point out some of the research issues unique to scaling up such DMIMO systems. We briefly review the significant technical progress in design and demonstration over the past few years, and describe a research agenda for the next few years based on fundamental questions in attaining the “distributed coherence” required to realize concept systems such as DMIMO communication at large carrier wavelengths (e.g., white space frequencies for which standard antenna arrays are too bulky) and distributed 911 for emergency and rescue scenarios.
In recent years, deep neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical
survey compactly summarises relevant work, much of it from the previous
millennium. Shallow and deep learners are distinguished by the depth of their
credit assignment paths, which are chains of possibly learnable, causal links
between actions and effects. I review deep supervised learning (also
recapitulating the history of backpropagation), unsupervised learning,
reinforcement learning & evolutionary computation, and indirect search for
short programs encoding deep and large networks.
Of several responses made to the same situation, those which are accompanied or closely followed by satisfaction to the animal will, other things being equal, be more firmly connected with the situation, so that, when it recurs, they will be more likely to recur; those which are accompanied or closely followed by discomfort to the animal will, other things being equal, have their connections with that situation weakened, so that, when it recurs, they will be less likely to occur. The greater the satisfaction or discomfort, the greater the strengthening or weakening of the bond. (Thorndike, 1911) The idea of learning to make appropriate responses based on reinforcing events has its roots in early psychological theories such as Thorndike's "law of effect" (quoted above). Although several important contributions were made in the 1950s, 1960s and 1970s by illustrious luminaries such as Bellman, Minsky, Klopf and others (Farley and Clark, 1954; Bellman, 1957; Minsky, 1961; Samuel, 1963; Michie and Chambers, 1968; Grossberg, 1975; Klopf, 1982), the last two decades have wit- nessed perhaps the strongest advances in the mathematical foundations of reinforcement learning, in addition to several impressive demonstrations of the performance of reinforcement learning algo- rithms in real world tasks. The introductory book by Sutton and Barto, two of the most influential and recognized leaders in the field, is therefore both timely and welcome. The book is divided into three parts. In the first part, the authors introduce and elaborate on the es- sential characteristics of the reinforcement learning problem, namely, the problem of learning "poli- cies" or mappings from environmental states to actions so as to maximize the amount of "reward"
Fundamen-tals of Massive MIMO
Sepp Hochreiter and Jürgen Schmidhuber
- Sepp Hochreiter
- Jürgen Schmidhuber
Uplink Power Control in Cell-Free Massive MIMO via Deep Learning
- C Andrea
- A Zappone
- S Buzzi
- M Debbah