Massive Multiple-input Multiple-output Research Articles

3D Antenna array for multi-user massive MIMO system to minimize unfavorable propagation

Unfavorable propagation in massive multiple input multiple output (MIMO) systems is an underlying channel condition that reduces the gains offered by the system in terms of parallel channels. This paper presents a study on different types of antenna array configurations at base station (BS) to minimize unfavorable propagation conditions. Unfavorable propagation results in increased correlation between channel vectors of two or more mobile terminals (MTs) which arises when the signals from two or more MTs have small angular separation and small angular spread. The study starts with the investigation of the conventional uniform linear array (ULA) under different propagation conditions using a geometrical channel model based on a single cluster of scatterers per MT to quantify the performance degradation in unfavorable propagation. Subsequently, the performance of other types of array geometries is investigated. A custom cluster-based geometrical channel model is used in this study which includes practical propagation aspects like multipath fading, shadow fading, and the effect of BS height. Further, the study considers two cases: micro-cell and macro-cell. Under space constraint settings in terms of the maximum dimension of the array, the proposed technique uses randomized antenna locations in the array to minimize the effect of unfavorable propagation. Based on the results on performance parameters like user correlation and capacity, the study reveals that an antenna array configuration comprising of elements distributed random-homogeneously in a spherical shell outperforms other configurations.

Impact of memory on beamforming optimization for DDPG-assisted RIS-multi-user system

Recently, reconfigurable intelligent surfaces (RIS) have garnered considerable attention as indispensable components driving the evolution of future 6G wireless communication systems. This heightened interest is primarily attributed to notable advancements in programmable meta-material fabrication, which enable the creation of highly versatile and adaptable surfaces. These surfaces, often referred to as intelligent reflecting arrays, represent a significant departure from the conventional capabilities of massive multiple-input multiple-output (MIMO) systems, thereby catalyzing the emergence of intelligent radio environments characterized by enhanced flexibility and efficiency. Our study is dedicated to the comprehensive exploration of coordinated design strategies that encompass both the transmission beamforming matrix at the base station and the phase shift matrix at the RIS. Leveraging recent breakthroughs in deep reinforcement learning (DRL), our approach harnesses the power of a Long Short-Term Memory (LSTM) based DRL algorithm. This algorithm orchestrates the joint design process through iterative interactions with the environment, strategically guided by predefined rewards operating within a continuous framework of states and actions. While recent research has underscored the efficacy of LSTM-based architectures in bolstering the learning capacity of reinforcement learning (RL) algorithms and simplifying the search process, our investigation reveals a nuanced insight. Contrary to prevailing trends, we find that the integration of memory into the Deep Deterministic Policy Gradient (DDPG) with LSTM (DDPG-LSTM) algorithm yields unexpected consequences, negatively impacting the system's overall performance. Through preliminary simulation results, we empirically demonstrate the adverse effect of memory on DDPG performance when applied to RIS systems. This finding not only sheds light on the complexities of optimizing 6G wireless communication systems but also underscores the importance of careful algorithmic design and parameter tuning in achieving desired outcomes in emerging technologies.

Hybrid Multiple Access Techniques Performance Analysis Of Dynamic Resource Allocation

The Non-Orthogonal Multiple Access (NOMA) and the Orthogonal Frequency Division Multiple Access (OFDMA) are promising techniques for next-generation wireless systems. Although much attention in the literature considered these techniques, an effective combination between such systems as hybrid multiple access (HMA) needs more attention. For this reason, this paper devotes to proposing two different scenarios of HMA using multi-user OFDM (MU-OFDM) and power domain (PD) NOMA for downlink transmission to overcome the limitations of both Orthogonal Multiple Access (OMA) and NOMA. Due to the randomness of a wireless channel, different user grouping strategies and dynamic power allocation (DPA) strategies are employed to satisfy users’ requirements. The proposed systems give high flexibility utilizing bitrate allocation and user fairness. System results show superior performance to traditional OMA and NOMA systems. The achieved variety of fairness is helpful for the diversity of applications which is a principal requirement for beyond-fifth-generation (B5G) networks. The next step in this analysis is to enhance the proposed systems’ spectral efficiency (SE) by introducing beamforming for massive Multiple-Input Multiple-Output (MIMO) systems. The bit error rate (BER) result of the proposed system achieves almost the same error floor with a benefit of approximately 10 dB signalto-noise ratio (SNR) when 90 resource blocks (RBs) are used.  

Dual-Driven Learning-Based Multiple-Input Multiple-Output Signal Detection for Unmanned Aerial Vehicle Air-to-Ground Communications

Unmanned aerial vehicle (UAV) air-to-ground (AG) communication plays a critical role in the evolving space–air–ground integrated network of the upcoming sixth-generation cellular network (6G). The integration of massive multiple-input multiple-output (MIMO) systems has become essential for ensuring optimal performing communication technologies. This article presents a novel dual-driven learning-based network for millimeter-wave (mm-wave) massive MIMO symbol detection of UAV AG communications. Our main contribution is that the proposed approach combines a data-driven symbol-correction network with a model-driven orthogonal approximate message passing network (OAMP-Net). Through joint training, the dual-driven network reduces symbol detection errors propagated through each iteration of the model-driven OAMP-Net. The numerical results demonstrate the superiority of the dual-driven detector over the conventional minimum mean square error (MMSE), orthogonal approximate message passing (OAMP), and OAMP-Net detectors at various noise powers and channel estimation errors. The dual-driven MIMO detector exhibits a 2–3 dB lower signal-to-noise ratio (SNR) requirement compared to the MMSE and OAMP-Net detectors to achieve a bit error rate (BER) of 1×10−2 when the channel estimation error is −30 dB. Moreover, the dual-driven MIMO detector exhibits an increased tolerance to channel estimation errors by 2–3 dB to achieve a BER of 1×10−3.

SEAttention-residual based channel estimation for mmWave massive MIMO systems in IoV scenarios

To improve the accuracy and efficiency of time-varying channels estimation algorithms for millimeter Wave (mmWave) massive Multiple-Input Multiple-Output (MIMO) systems in Internet of Vehicles (IoV) scenarios, the paper proposes a deep learning (DL) algorithm, Squeeze-and-Excitation Attention Residual Network (SEARNet), which integrates Squeeze-and-Excitation Attention (SEAttention) mechanism and residual module. Specifically, SEARNet considers the channel information as an image matrix, and embeds a SEAttention module in residual module to construct the SEAttention-Residual block. Through a data-driven approach, SEARNet can effectively extract key information from the channel matrix using the SEAttention mechanism, thereby reducing noise interference and estimating the channel in an accurate and efficient manner. The simulation results show that compared to two traditional and two DL channel estimation algorithms, the proposed SEARNet can achieve a maximum reduction in normalized mean square error (NMSE) of 97.66% and 84.49% at SNR of -10 dB, 78.18% at SNR of 5 dB, and 43.51% at SNR of 10 dB, respectively.

Impact of Hardware Impairment on the Joint Reconfigurable Intelligent Surface and Robust Transceiver Design in MU-MIMO System

Reconfigurable intelligent surface (RIS) is a revolutionary passive radio technique to facilitate capacity enhancement beyond the current massive multiple-input multiple-output (MIMO) transmission. However, the potential hardware impairment (HWI) of the RIS usually causes inevitable performance degradation and the amplification of imperfect CSI. These impacts still lack full investigation in the RIS-assisted wireless network. This paper developed a robust joint RIS and transceiver design algorithm to minimize the worst-case mean square error (MSE) of the received signal under the HWI effect and imperfect channel state information (CSI) in the RIS-assisted multi-user MIMO (MU-MIMO) wireless network. Specifically, since the proposed robust joint RIS and transceiver design problem yields non-convex characteristics under severe HWI, an iterative three-step convex algorithm is developed to approach the optimality by relaxation and convex transformation. Compared with the state-of-the-art baselines that ignore the HWI, the proposed robust algorithm inhibits the destruction of HWI while raising the worst-case MSE effectively in several numerical simulations. Moreover, due to the properties of the HWI, the performance loss is notable under the magnification of the number of reflected elements in the RIS-assisted MU-MIMO wireless network.

Joint beamforming and power splitting design for MISO downlink communication with SWIPT: a comparison between cell-free massive MIMO and small-cell deployments

Simultaneous wireless information and power transfer (SWIPT) has been advocated as a highly promising technology for enhancing the capabilities of 5G and 6G devices. However, the challenge of dealing with large propagation path loss poses a significant hurdle. To address this issue, massive multiple-input multiple-output (MIMO) is employed to enhance the efficiency of SWIPT in cellular-based networks with multiple small cells, and especially increase the energy for cell-edge users. In addition, by leveraging a large set of spatially distributed base stations to collaboratively serve SWIPT-enabled user equipment, the cell-free massive MIMO has the potential to provide even better performance than the conventional small-cell systems. In this work, we extend the investigation to include the application of SWIPT technology with alternating current (AC) logic in the cell-free networks and the small-cell networks and propose joint beamforming and power splitting optimization frameworks to maximize the system sum-rate, subject to the constraints on harvested energy, AC logic energy supply, and total transmit power. The optimization problem is shown to be non-convex, posing a significant challenge. To address this challenge, we resort to a two-stage decomposition approach. Specifically, we first introduce quadratic transform-based fractional programming (FP) algorithms to iteratively solve the non-convex optimization problems in the first stage, achieving near-optimal solutions with low time complexities. To further reduce the complexities, we also incorporate conventional schemes such as zero forcing, maximum ratio transmission, and signal-to-leakage-and-noise ratio for the design of beamforming vectors. Second, to determine the optimal power splitting ratio within the framework, we develop a one-dimensional (1-D) search algorithm to tackle the single variable optimization problem reduced in the second stage. These algorithms are then evaluated in the context of cell-free MIMO and small-cell networks with numerical experiments. The results show that the FP-based algorithms can consistently outperform those utilizing the conventional beamforming schemes, and the solutions of this work can achieve up to fivefold improvement in the system sum-rate than the small-cell counterpart while providing different but comparable performance trends in energy harvesting (EH).

Energy-Efficient Access Point Selection Scheme for Reconfigurable-Intelligent-Surface-Assisted Cell-Free Massive MIMO Systems

Reconfigurable intelligent surface (RIS)-assisted cell-free (CF) massive Multiple-Input Multiple-Output (MIMO) technology exhibits significant potential in enhancing the energy efficiency of 6G mobile communications. Nevertheless, recent studies suggest that both access points (APs) and RISs encounter challenges related to a high energy consumption during operation. To address this issue, strategies involving AP hibernation and RIS shut-off are proposed. Subsequently, an optimization problem is formulated to jointly optimize RISs, beamforming vectors, and AP selection with the aim of maximizing the energy efficiency (EE). Initially, the non-convex optimization problem for maximizing energy efficiency is decomposed into three sub-problems. These sub-problems are subsequently reformulated using fractional programming and variational programming techniques and then solved using the successive convex approximation (SCA) algorithm, Dinkelbach algorithm, and greedy algorithm, respectively. Subsequently, an alternate optimization algorithm based on block gradient descent is introduced to iteratively solve the four-variable optimization problem, thereby obtaining an approximate solution to the original problem. The simulation results demonstrate that the algorithm significantly reduces energy consumption. Specifically, compared to the scheme without the hibernation strategy, the energy efficiency (EE) is enhanced by 35%.

Leveraging 5G Network Capabilities for Smart Grid Communication

This paper presents a comprehensive investigation into the architecture and components of 5G networks, focusing on their suitability for smart grid applications. With the increasing complexity and demands of modern energy infrastructure, there is a growing need for reliable and low-latency communication systems to support critical smart grid operations. This paper explores key features of 5G networks, including network slicing, massive MIMO (Multiple Input Multiple Output), and low-latency communication protocols like URLLC (Ultra-Reliable Low Latency Communication), and examines how these features can be harnessed to address the unique requirements of smart grid environments. Through a detailed analysis of each component, this paper sheds light on the design considerations, deployment strategies, and performance implications of leveraging 5G technology for smart grid communication. Furthermore, practical insights, challenges, and future research areas are discussed to guide the development of next-generation smart grid solutions.

Machine Learning-Based Beamforming Algorithm for Massive MIMO Systems in 5G Networks

The following research focuses on the use of machine learning-based beamforming algorithms to improve Massive Multiple Input Multiple Output (MIMO) systems in 5G networks. Four unique algorithms namely, the Deep Learning Beamforming Algorithm (DLBA), Reinforcement Learning-Based Doa Estimation Algorithm (RLBEA), Clustering based beam forming algorithm(CBA) and GeneticAlgorithm Based Beam Forming Algoeithm were developed after which each of them was undertook evaluation. Widespread trials, in a simulated 5G environment, have revealed that the DLBA and RLBA considerably outperform other technologies by means of system throughput SINR as well Both the DLBA and RLBA achieved high system throughput, increased SINR levels and low BER. CBA and GABA, using clustering and genetic algorithms as their approaches, displayed moderate values on all assessed composite measures. This research offers important insights on the adaptability and learning potential of machine-learning based beamforming algorithms highlighting their ability to improve efficiency in wireless communication networks during the 5G revolution

Joint user association, service caching, and task offloading in multi-tier communication/multi-tier edge computing heterogeneous networks

Due to the wide range of intensive computational applications and ubiquitous connectivity of the Internet of Things (IoT) paradigms, it has become crucial to develop a new platform that can achieve low delay, high network throughput, and enhanced quality of service (QoS). This paper proposes a joint user association, service caching, and task offloading strategy to reduce delay and enhance users’ QoS in multi-tier communication and multi-tier edge computing heterogeneous networks (HetNets). The considered system model consists of multi-users with different tasks and service data sizes communicating in a heterogeneous network of one massive multiple-input multiple-output (M-MIMO) macro base station and some small base stations. The proposed work investigates user association, power allocation, optimum service data caching, and task offloading strategies at the computing network edges. Thereby, the objectives of this work are to propose an efficient framework to reduce the system delay, increase the network throughput, and meet the user requirements in multi-tier communication and multi-tier edge computing heterogeneous networks. The simulation results show that the proposed algorithm outperforms the state-of-the-art with a 49.48% decrease in system delay, 80% reduction in cost and hardware complexity in terms of the reduced number of installed antennas, and 48.58% enhancement in the network throughput.

A compressed 2D-DOA and polarization estimation algorithm for mmWave polarized massive MIMO systems

Due to providing greater degrees-of-freedom (DOFs) and securer communication guarantees than traditional scalar array, polarized massive multiple-input multiple-output (MIMO) technique offers a prospective insight into millimeter-wave (mmWave) communication. In this paper, a compressed two-dimensional (2D) direction-of-arrival (DOA) and polarization estimation algorithm combining the compressive sampling propagator method with reduced-dimension multiple signal classification (CSPM-RDMUSIC) is developed for mmWave polarized massive MIMO systems. First, a synchronous compressive network is constructed to compress the high-dimensional output into a low-dimensional one. Thereafter, a propagator is structured to acquire the signal subspace. Subsequently, accurate 2D-DOA and polarization estimation are achieved using a coarse-refined strategy, where the vector cross-product technology is investigated for coarse 2D-DOA estimation and then RDMUSIC is exploited to perform 2D local search for accurate parameter estimation. Owing to integrating the CSPM framework with the RDMUSIC strategy, the developed approach provides high-precision parameter estimation with relative computational economy, supporting mmWave communication demands. What's more, it's suitable for arbitrary array geometry with high flexibility. Several experimental results validate the superiorities of the developed framework.

Performance analysis and comparison of a novel Steiner-Quadrature Space Shift Keying (S-QSSK) scheme in massive MIMO systems

This paper introduces Steiner-quadrature space shift keying (QSSK) (S-QSSK), an innovative modulation scheme tailored for multiple–input multiple–output (MIMO) systems. The study compares S-QSSK with existing modulation schemes (S-space shift keying (SSK)(S-SSK), QSSK, generalized quadrature space shift keying (GQSSK)) across various performance metrics, considering diverse channel conditions, transmit antenna numbers, and spectral efficiencies. Theoretical average bit error rate (ABER) analysis, validated by Monte Carlo simulations, establishes a close agreement between analytical and practical results, especially at realistic signal-to-noise-ratio (SNR) values. Additionally, capacity and mutual information formulas shed light on the system’s information transmission capabilities. The research delves into the outage probability, power consumption, and computational complexity of S-QSSK MIMO systems. It unveils a promising trade-off, demonstrating that S-QSSK achieves competitive performance in ABER, capacity, and mutual information, positioning it as a practical modulation technique. Importantly, S-QSSK exhibits about a 1 dB ABER performance decrease compared to S-SSK and QSSK, while offering a noteworthy 2 dB improvement over GQSSK. Despite requiring slightly more transmit antennas than GQSSK, S-QSSK demands significantly fewer than both S-SSK and traditional QSSK, particularly when targeting high spectral efficiencies. Moreover, the analysis underscores the advantageous power consumption and favorable computational complexity of S-QSSK relative to other modulation schemes. The proposed S-QSSK MIMO system thus presents itself as an efficient solution, enabling high data rates with fewer transmit antennas, resulting in substantial reductions in power consumption and computational complexity without a significant sacrifice in ABER and mutual information. These attributes make it a compelling choice for various applications, including those requiring efficient massive multiple–input multiple–output (mMIMO) operations.

Optimization of Signal Detection Using Deep CNN in Ultra-Massive MIMO

This paper addresses the evolving landscape of communication technology, emphasizing the pivotal role of 5G and the emerging 6G networks in accommodating the increasing demand for high-speed and accurate data transmission. We delve into the advancements in 5G technology, particularly the implementation of millimeter wave (mmWave) frequencies ranging from 30 to 300 GHz. These advancements are instrumental in enhancing applications requiring massive data transmission and reception, facilitated by massive MIMO (multiple input multiple output) systems. Looking towards the future, this paper forecasts the necessity for faster data transmission technologies, shifting the focus toward the development of 6G networks. These future networks are projected to employ ultra-massive MIMO systems in the terahertz band, operating within 0.1–10 THz frequency ranges. A significant part of our research is dedicated to exploring advanced signal detection techniques, helping to mitigate the impact of interference and improve accuracy in data transmission and enabling more efficient communication, even in environments with high levels of noise, and including zero forcing (ZF) and minimum mean square error (MMSE) methods, which form the cornerstone of our proposed approach. Additionally, signal detection contributes to the development of new communication technologies such as 5G and 6G, which require a high data transmission efficiency and rapid response speeds. The core contribution of this study lies in the application of deep learning to signal detection in ultra-massive MIMO systems, a critical component of 6G technology. We compare this approach with existing ELMx-based machine learning methods, focusing on algorithmic efficiency and computational performance. Our comparative analysis included the regularized extreme learning machine (RELM) and the outlier robust extreme learning machine (ORELM), juxtaposed with ZF and MMSE methods. Simulation results indicated the superiority of our convolutional neural network for signal detection (CNN-SD) over the traditional ELMx-based, ZF, and MMSE methods, particularly in terms of channel capacity and bit error rate. Furthermore, we demonstrate the computational efficiency and reduced complexity of the CNN-SD method, underscoring its suitability for future expansive MIMO systems.

Privacy and convergence analysis for the internet of medical things using massive MIMO

Machine learning is the analysis based on data that gives strategic decisions to cultivate an accurate and stable framework for different applications. Access to medical data with the utmost privacy and high data rates is still a challenging problem. To accomplish the above-mentioned features, the performance of federated learning (FL) with 5G massive multiple-input-multiple-output (MIMO) is investigated for IoMT systems. This provides an energy-efficient and privacy-preserving solution with high throughput for digital health system. In the proposed model, the uplink scenario is investigated using different detection techniques. The performance are evaluated at the central server and edge devices for different signal-to-noise ratios (SNRs) and different fading channels. The ML bit error rate (BER) is better than MRC but with higher complexity. The accuracy obtained is approximately 90% with an improvement of around 8% to 9% as compared to the baseline approach.

Channel estimation for pilot contamination in massive MIMO-NOMA system

Channel estimation is crucial for massive multiple-input multiple-output (MIMO) systems to scale up multi-user (MU) MIMO, providing great improvement in spectral and energy efficiency. The nature of non-orthogonal cause pilot contamination is experienced only while estimating multi-cell MIMO scheme with the training and it is misplaced while narrowing concentration to multi-cell or one-cell setting, where information of the channel is assumed to be obtainable at no cost. Non-orthogonal multiple access (NOMA) serves numerous users concurrently utilizing channel gain differences. The advancement in massive MIMO-NOMA technology has offered diverse techniques recently for reducing pilot contamination in massive MIMO-NOMA based on pilot allocation. Here, a new approach called War Strategy Chimp Optimization+Deep Neuro-Fuzzy Network (WSChO+DNFN) is designed for the estimation of channels to reduce pilot contamination in a massive MIMO-NOMA system. It takes place in two phases, the transmitter and the receiver phase. The channel estimation is conducted by DNFN that is tuned by devised WSChO. Furthermore, WSChO is an amalgamation of War Strategy Optimization (WSO) and Chimp Optimization Algorithm (ChOA). Additionally, the WSChO+DNFN attained minimal values of BER and normalized MSE of 0.000103 and 0.000074, respectively. The proposed method has achieved a performance gain of 44.39%, 19.26%, 9.17%, 5.22%, 9.92%, and 6.03% compared to the Orthogonal Frequency Division Multiplexing (OFDM), Group Successive Interference Cancellation assisted Semi-Blind Channel Estimation Scheme (GSIC_SBCE), Sector-Based Pilot Assignment Scheme (PAS), Convolutional Neural Network (CNN), User Segregation based Channel Estimation (USCE), Optimal Channel Estimation using Hybrid Machine Learning (OCE_HML), respectively.

Potential Impact of 5G Technology on Various Aspects of Technology Development

The introduction of fifth-generation (5G) wireless systems marks an important milestone in the development of wireless communications. This development has the potential to revolutionize many industries and improve our daily lives. Our research paper aims to come up with an inclusive overview of the prospects and developments in 5G wireless systems. It provides an in-depth look at key issues, trends, and testing directions that will shape 5G network development and deployment in the years to come. Our research papers cover a wide range of topics, including networking, spectrum usage, device-to-device communication, massive MIMO, edge computing, security, and 5G technologies. We review the present state of research and ongoing projects, providing insight into the future of 5G wireless systems and their impact on society. As experts, we guarantee that our content will be effective, unique, engaging, and tailored to your specific needs and requirements. The demand for quick, more dependable wireless connections continues to increase, making the development and implementation of fifth-generation (5G) wireless networks more difficult. In this article, we provide a comprehensive overview of ongoing and future research in 5G wireless technology, highlighting key challenges and solutions. We are investigating the multiple input multiple output (MIMO) field where no antenna can be used to improve spectral efficiency and coverage. We examine the optimization of antenna configurations, beamforming strategies, and resource allocation strategies to maximize the advantage of large MIMO when addressing network devices and systems. Additionally, we are exploring the potential of millimeter wave (mm-Wave) communications to provide maximum data and bandwidth, and the integration of shared networks (HetNets) to improve service and capacity. We will also touch on the emergence of edge computing leading to poor quality applications and reduced network collaboration in 5G networks, and the importance of network connectivity that allows the physical network infrastructure to be divided into several sessions with different characteristics. By solving problems in these areas, we strive to unlock the full potential of 5G networks to transform the industry and pave the way for advanced and intelligent connectivity in the future.

Low complexity hybrid beamforming for downlink multi-user MIMO OFDM systems

Hybrid beamforming is critical for massive multiple input multiple output (MIMO) to achieve high spectral efficiency at reduced hardware cost. Existing hybrid beamforming schemes either design the analog beamforming and digital beamforming separately, or jointly optimize them through alternating optimization. Such strategies incur non-negligible performance degradation or huge computational complexity in optimization, which is especially evident with the partially connected architecture. In this work, we consider a general downlink multi-user MIMO orthogonal frequency division multiplexing (OFDM) system with the hybrid beamforming architecture, where finite-resolution phase shifters are adopted. We propose an efficient beamforming strategy on the sum rate maximization criterion. Rather than eliminating the interference entirely by digital beamforming, we optimize the analog beamforming by considering the interference at the same time. We consider a fixed digital beamforming structure to reduce the overall complexity. Given the fact of finite-resolution phase shifters, the analog beamforming is optimized over discrete phase values. Compared to existing hybrid beamforming designs, the proposed algorithm achieves much improved performance. By applying the average channel covariance to the analog beamforming design, the computational complexity of the proposed algorithm is further reduced. Meanwhile, the proposed algorithm is applicable to both fully and partially connected architectures.

Learning to optimize power allocation in cell-free massive MIMO networks with hybrid green energy

In cell-free (CF) massive multiple-input multiple-output (MIMO) networks, many access points (APs) simultaneously serve user equipment (UEs) using the same time and frequency resources. The resource allocation algorithm in such networks needs to handle many calculations within a limited time frame to determine the power allocation from each AP to each UE. Further, the dispersion and large number of APs in CF massive MIMO networks pose challenges in terms of energy supply. As access to the power grid may be limited, renewable energies are often required as a supplement. However, due to the non-deterministic nature of the charging process, the resource allocation algorithm needs to consider the dynamic and uncertain amount of energy available at the APs. In this article, we propose a scalable machine learning based on the emerging Learning to Optimize (L2O) paradigm that utilizes neural networks (NNs) for resource allocation in CF massive MIMO networks powered by electrical and renewable energies. Our objective is to minimize energy consumption from the power grid while satisfying the spectral efficiency (SE) constraints of the UEs. Additionally, our algorithm adopts a forward-looking approach and employs a green energy budgeting mechanism to prevent service interruption at green APs during energy shortages. Our algorithm design approach involves formulating the offline version of the problem as a second-order cone program (SOCP). Subsequently, we train an NN using the solutions obtained from solving the online variant of the SOCP. Our results indicated that our L2O-based algorithm can accurately mimic the solutions of the optimization problem with significantly reduced computational complexity.

A deep learning approach based on Richardson and Gauss–Seidel for massive MIMO detection

AbstractMassive multiple‐input multiple‐output (MIMO) systems can improve the spectrum utilization and the system capacity, but this also increases the computational complexity of the signal detection. The existing iterative algorithms can greatly reduce the computational complexity; however, the detection performance is limited. In order to achieve a better balance between the computational complexity and the detection performance, this article combines the model‐driven deep learning approached with Massive MIMO signal detection to construct RGNet (RIGS‐based deep learning Network). First, RIGS is proposed as a hybrid method of RI (Richardson) and GS (Gauss–Seidel). The RIGS algorithm combines these methods to achieve faster convergence. However, the performance of RIGS joint algorithm is limited to the spatially correlated channel scenarios. To improve robustness, we further extend RIGS, by adding learnable parameters in each iteration and introducing staircase activation functions to significantly improve detection performance. Simulation results show that the proposed RGNet has low computational complexity and a simple and fast training process. It can also achieve excellent detection performance in Rayleigh fading channel and spatially correlated channel.