Massive MIMO Research Articles

Minimizing Energy Consumption in Cell-Free Massive MIMO Networks

Minimizing Energy Consumption in Cell-Free Massive MIMO Networks

Enhancing 5G massive MIMO systems with EfficientNet‐B7‐powered deep learning‐driven beamforming

AbstractThe development of wireless communication systems is a challenging and constantly evolving field and the issue of gaining optimal performance is of utmost importance. This work intends to give a thorough and detailed description of massive MIMO technology and its properties, with a significant emphasis on digital beamforming (FDB) and hybrid beamforming (HBF) techniques and the potential of combining them with the most recent and exciting frontier of research: deep learning. On one hand, FDB provides accurate signal control but, on the other hand, it deals with substantial needs like high‐power consumption. This challenge makes the focus shift to HBF—the innovative technology successfully coupled with deep learning's powerful potential. The chosen research explores extensively the major areas of application and compatibility of this operating mode in a diverse range of operational situations in the interference environment as well as in different levels of noise conditions. Moreover, the study offers a comprehensive comparison, which is highly effective in exploring further methods that focus on improving spectral efficiency. Significantly, the “Proposed Method” is suggested to be at the leading position, which demonstrates superior performance. Showing outstanding generalization capability, versatile robustness, and efficiency of usage in the proposed framework rely on EfficientNet‐B7 as the major portion. This makes it adaptive to its dynamic surroundings and puts it as a powerful tool in the world of advanced connectivity and massive MIMO technology. Due to its core ability to respond to changes in conditions effectively and efficiently, the proposed framework is seen as one of the most powerful approaches that could be used to change wireless communication systems.

Power-efficient full-duplex near user with power allocation and antenna selection in NOMA-based systems

This paper proposes a power scaling (PS) technique aimed at mitigating the outage floor problem commonly encountered in multi-user full-duplex (FD) non-orthogonal multiple access (NOMA) systems. Two antenna modes denominated as adaptive antenna mode (AAM) and fixed antenna mode (FAM) are utilized in this work for L FD near users in close proximity. In addition, a combined method of selecting both antenna mode and near user integrated with PS is employed to improve the overall network performance. Moreover, a power allocation between the chosen near user and far user is considered. In the low-to-moderate power regions, by AAM and FAM, we achieve twice of full diversity gain and full diversity gain, respectively. The research presents mathematical expressions for deriving the average capacity and outage probability and supports the theoretical findings with simulation-based evidence. The results of this work show that PS method not only contributes to a greater spatial diversity but also leads to superior performance compared to traditional FD NOMA systems. Moreover, our proposed method overcomes the outage floor and capacity ceiling. Furthermore, the work can be developed to 6G massive MIMO technology in multi-user FD cooperative NOMA systems.

Hybrid CNN-transformer network for efficient CSI feedback

In recent years, many deep learning-based methods have been utilized for the feedback of Channel State Information (CSI) in massive MIMO systems. The Transformer-based networks leverage global self-attention mechanisms that can effectively capture remote correlations between antennas, while Convolutional Neural Networks (CNNs) excel in acquiring local information. To balance the advantages of both, this paper proposes an Efficient Feature Aggregation Network called EFANet, which hybrid CNNs and Transformer. Specifically, we propose a Refined Window Multi-head Self-Attention (RW-MSA) through hybrid Convolutional Embedding Unit (CEU) and Window Multi-head Self-Attention (W-MSA) to reduce information loss between windows and achieve efficient feature aggregation. Additionally, we develop a Local Enhanced Feedforward Network (LEFN) to further integrate local information in the CSI matrix and model detailed features of different regions. Finally, the Compensation Unit (CU) is designed to further compensate for global-local features in the CSI matrix. Through the above design, the global and local features are fully interactive to reduce information loss. Numerous experiments have shown that the proposed method achieves better CSI reconstruction performance while reducing computational complexity.

Millimeter Wave Massive MIMO systems using Hybrid Beamforming

The goal of next-generation wireless systems is to support many users by achieving higher data rates and reduced latency. Multiple input and multiple output systems (MIMO) are utilized in order to achieve high data rates. Multiple antennas are employed by Massive MIMO systems in both the transmitter along with the receiver. A signal processing method known as beamforming is used on several transmitting and receiving stations in order to deliver and receive multiple messages at once. To increase spectral efficiency, hybrid beamforming using a uniform rectangular antenna array is used in this research work. The results of hybrid beamforming using different numbers of antennas are compared with those of fully digital beamforming. A comparison between signal-to-noise (SNR) and bit error rate (BER) is performed. Comparing hybrid beamforming to fully digital beamforming, simulation findings show that hybrid beamforming reduces computing complexity due to reduced number of RF links. Also observed that the spectral efficiency rises with an increase in the quantity of transmitting antennas.

User Association in User-Centric Hybrid VLC/RF Cell-Free Massive MIMO Systems

User Association in User-Centric Hybrid VLC/RF Cell-Free Massive MIMO Systems

Deep Learning based enhanced hybrid beamforming using RSSI signals in MIMO systems

Hybrid beamforming has gained popularity in recent years due to its ability to enhance the performance of massive multiple-input multiple-output (massive MIMO) systems and improve the efficiency of wireless communication. However, designing a hybrid precoder is a challenging task as it requires accurate channel state information (CSI) and needs to solve an optimization problem. This paper introduces an unsupervised hybrid deep learning technique, namely CNN-BiLSTM, for developing hybrid beamforming in massive MIMO systems based on received signal strength indicator (RSSI) without having prior knowledge of CSI. Additionally, incremental principal component analysis (Incremental PCA) is used to reduce the dataset's dimensionality. The results of our proposed model demonstrate a significant improvement in spectral efficiency. This technique reduces the training overhead significantly and is able to quickly serve all the users. The simulation results indicate that proposed model produces low side lobes when providing coverage to areas. As a result, the performance of our model has a noticeable advantage compared to other models. In addition, proposed method achieves 99.21% accuracy and 5.30 bps/Hz sum-rate that is close to optimal performance and outperforms the state-of-the-art method.

Efficient resource allocation using whale optimization for cell-free massive MIMO networks in 6G HetNet

The increase in data rate demands has driven the development of Cell-Free massive Multiple-Input Multiple-Output (CFmMIMO) technology in 6G Heterogeneous Networks (HetNets). This paper proposes an integration of Unmanned Aerial Vehicles (UAVs) and Device-to-Device (D2D) communication in CFmMIMO, aiming to enhance network capacity, coverage, and service delivery in next-generation wireless networks. The paper investigates uplink transmission in a network where Access Points (APs) have imperfect channel state information. It considers Cell-free User Equipment (CUE), UAVs, and D2D pairs, deriving closed-form uplink achievable rates for each user type. Moreover, two optimization problems are formulated to enhance user data rates: one focuses on maximizing the sum data rate through pilot assignment, while the other aims to achieve weighted max–min power control through power allocation. Furthermore, to address these problem, we propose a Modified Whale Optimization Algorithm (MWOA) and a novel Pilot Assignment based on Whale Optimization Algorithm (PAWOA). Performance studies demonstrate significant improvements over state-of-the-art algorithms.

A Survey of Federated Learning for mmWave Massive MIMO

A Survey of Federated Learning for mmWave Massive MIMO

Energy Efficiency Optimization of Cell-Free Massive MIMO with Zero Forcing Precoding

Energy Efficiency Optimization of Cell-Free Massive MIMO with Zero Forcing Precoding

Performance Evaluation of Precoding Schemes for Multi User Massive MIMO System Over Nakagami-m Fading Channel

Performance Evaluation of Precoding Schemes for Multi User Massive MIMO System Over Nakagami-m Fading Channel

Precoder Design for Network Massive MIMO Optical Wireless Communications.

Precoding is a technique employed to enhance transmission rates in various communication systems, including massive multiple-input multiple-output (MIMO) and optical wireless communication (OWC). In this study, we focus on network massive MIMO OWC (NM-MIMO-OWC) systems and investigate the precoder design to enhance the sum rate and improve the system performance. We present the network's massive MIMO OWC framework. By utilizing this framework, we are able to calculate the achievable sum rate. Subsequently, we consider the precoding design for maximizing the sum rate while adhering to the total power constraint. To solve this optimization problem, we provide a necessary condition of the optimal solution based on the Karush-Kuhn-Tucker (KKT) conditions, and propose a low-complexity algorithm to further enhance the efficiency of the proposed precoding technique. The numerical results demonstrate that the proposed precoder design significantly improves the transmission rate and effectively maximizes the sum rate.

Implementation of Massive Multiple-Input Multiple-Output (MIMO) 5G Communication System using Modified Least-Mean-Square (LMS) Adaptive Filters Algorithm

The massive MIMO systems are the more popular field in the present era for the 5G wireless communication system. The MIMO system is a demanding research topic for the last four decades. This topic is under implementation and observation from the last few years. These systems have many advantages and many research sub-areas but this paper investigates the modified model of the massive MIMO receiver system. The traditional receiver system model of massive MIMO system reduces the channel noise using a linear filter in the receive combiner bank (RCB) but the proposed model removes the channel noise before the RCB using an adaptive filter bank (AFB). The AFB is the combination of LMS adaptive filters. The analysis parameters are channel noise, signal-to-noise ratio (SNR) and bit-error-rate (BER) using the hybrid precoder and combiner computation algorithms – Quantized Sparse Hybrid Beamforming (QSHB) and Hybrid Beamforming Peak Search (HBPS). Therefore, the proposed massive MIMO system model gives the less channel noise in the received signal, higher SNR and lower BER as compared to the traditional massive MIMO receiver systems.

Innovative resource allocation mechanism for optimizing 5G multi user‐massive multiple input multiple output system

Abstract5G networks are essential in all locations owing to the multitude of advantages they provide. As a result, the number of users has increased dramatically. Nevertheless, these users require a variety of resources in order to function efficiently. Deep learning techniques have been created to improve the precision and dependability of resource allocation in the context of 5G networks. This research utilizes an efficient recurrent neural network (ERNN) to handle resource allocation for 5G multiuser (MU)‐massive multiple input multiple output (MIMO). In order to optimize the objective functions, the first application of the multi‐objective differential evaluation algorithm (MODEA) is used. The neural network is provided with these updated goal functions in order to allocate resources. ERNN evaluates the level of need for each individual user. By partitioning the resource at this level, it maintains a high throughput while distributing it to each user. In addition, the fairness index of the resource distribution system based on neural networks is established. The suggested method achieves a data transfer rate of 290 bits per second (bps) and a fairness index of 0.97% when used by 50 users. The findings of the proposed method exhibit superior performance compared to other existing methods in the field of 5G massive MIMO.

Performance of Massive MIMO Aided by Reflective Intelligent Surfaces

Performance of Massive MIMO Aided by Reflective Intelligent Surfaces

User-Centric Cell-Free Massive MIMO with Low-Resolution ADCs for Massive Access.

This paper proposes a heuristic association algorithm between access points (APs) and user equipment (UE) in user-centric cell-free massive multiple-input-multiple-output (MIMO) systems, specifically targeting scenarios where UEs share the same frequency and time resources. The proposed algorithm prevents overserving APs and ensures the connectivity of all UEs, even when the number of UEs is significantly greater than the number of APs. Additionally, we assume the use of low-resolution analog-to-digital converters (ADCs) to reduce fronthaul capacity. While realistic massive access scenarios, such as those in Internet-of-Things (IoT) environments, often involve hundreds or thousands of UEs per AP using multiple access techniques to allocate different frequency and time resources, our study focuses on scenarios where UEs within each AP cluster share the same frequency and time resources to highlight the impact of pilot contamination in dense network environments. The proposed algorithm is validated through simulations, confirming that it guarantees the connection of all UEs and prevents overserving APs. Furthermore, we analyze the required fronthaul capacity based on quantization bits and confirm that the proposed algorithm outperforms existing algorithms in terms of SE and average SE performance for UEs.

Analysis of Reduced Quantized Feedback-Based User-Antenna Scheduling Scheme for Multi-user Massive MIMO FDD Systems

Analysis of Reduced Quantized Feedback-Based User-Antenna Scheduling Scheme for Multi-user Massive MIMO FDD Systems

Enhancing spectral efficiency in uplink/downlink channels of multi-cell massive MIMO for 5G networks

Massive multiple-input multiple-output (MIMO) systems are at the forefront of 5G technology, significantly improving energy efficiency compared to earlier wireless communication systems. This study develops an optimal model for energy-efficient massive MIMO systems, aiming to increase spectral efficiency (SE) within a multi-cell framework. Base stations (BSs) use various techniques for channel estimations during uplink (UL) transmission, including minimum mean-squared error (MMSE), Least Squares, and Element-wise MMSE (EW-MMSE) estimators. The research evaluates the SE achievable through MMSE channel estimation by applying different receive combining schemes. Additionally, it explores downlink (DL) transmission using various precoding schemes, utilizing vectors similar to those in combining schemes. Simulations show a significant improvement in SE by advancing UL and DL transmission models. The study highlights that optimized MMSE channel estimation, along with an increased number of BS antennas and the ability to serve multiple user equipment (UEs) per cell, can enhance the average SE per cell. The findings indicate that optimizing channel estimation is crucial for the development of massive MIMO systems, especially for improving SE in both UL and DL transmissions.

Dynamic Unsourced Random Access With Massive MIMO

Dynamic Unsourced Random Access With Massive MIMO

Integrated Sensing and Communication With Massive MIMO: A Unified Tensor Approach for Channel and Target Parameter Estimation

Integrated Sensing and Communication With Massive MIMO: A Unified Tensor Approach for Channel and Target Parameter Estimation