Massive Machine-Type Communication (mMTC) is a critical Internet of Things (IoT) scenario in 5G and beyond 5G (B5G) wireless networks, characterized by a vast number of devices, smaller data packets, sporadic transmission, and diverse latency requirements. Massive multiple-input-multiple-output (MIMO) technology allows multiple user equipments (UEs) to transmit their data simultaneously over the same resource block, making it a promising technology to support mMTC. However, when massive UEs attempt to access the massive MIMO network simultaneously, the network will experience severe overload. To address this challenge, we propose a Deep Deterministic Policy Gradient (DDPG)-based delay-aware Access Class Barring (ACB) dynamic access control scheme for mMTC in massive MIMO networks. In this scheme, we model the access blocking probability as a function of latency sensitivity for each active UE with a shared parameter, ensuring that the closer the current delay is to a UE’s delay budget, the higher the access priority of that UE. We then propose a DDPG-based algorithm to optimize the access blocking probability and the access blocking time in ACB. Simulation studies demonstrate that, compared with the baseline methods, the proposed scheme significantly increases the number of successful access UEs while maintaining access delays within the budget constraints.

In this work, we investigate the frequency synchronization and system performance in massive multiple-input multiple-output (MIMO) systems with one-bit analog-to digital converters (ADCs). First, we tackle the challenges arising from severe multi-user interference (MUI) and the non-linearity inherent in one-bit ADCs in orthogonal frequency division multiplexing (OFDM) based on Bussgang decomposition and receive beamforming. To assess the accuracy of the CFO estimation, we analyze its theoretical mean square error (MSE) and investigate how quantization noise influences synchronization precision. Additionally, we introduce a multi-user inference (MUI)-plus-noise whitening technique to mitigate the correlation of the equivalent noise. Finally, we derive an approximate expression for the uplink achievable rate using maximal-ratio combining (MRC) detection scheme. Extensive numerical simulations confirm the effectiveness of the proposed approach.

Petrophysics estimates reservoir parameters based on formation reflections, but generally neglect porosity heterogeneity. In the Berryman theory, pore aspect ratio is considered in petrophysical modeling. As we cannot acquire pore aspect ratio directly, so a fixed value is set empirically without considering the heterogeneity of reservoir. We propose pore aspect ratio correction through Hunger Games Search (HGS). HGS quickly develops the optimal solution space for pore aspect ratio by simulating the way social animals forage. The revised pore aspect ratio improves the accuracy of forward modeling. In the new rock physics modeling with revised pore aspect ratio, the correlation coefficient for P wave velocity improved from 0.843 to 0.924, and for S wave velocity from 0.784 to 0.857. We added the revised pore aspect ratio to the petrophysical inversion process. A bidirectional long-short-term memory network is established to realize the joint inversion of multiple reservoir parameters considering the heterogeneity of porosity. The proposed scheme was applied in tight sandstone reservoir. The results show that the physical parameters and pore space structure can be effectively inverted.

In this article, we present a random access (RA) scheme for federated learning (FL) over massive multiple-input–multiple-output (MIMO) systems to tackle the issue of some local devices not being able to compute their local models. This scheme adopts a multichannel model and allows devices to randomly select their uploading channels, and then the base station (BS) aggregates the local models received from channels directly based on the over-the-air computation. We call this scheme as RA-based FL over massive MIMO (RAFL-MIMO). Furthermore, to enable more devices to be involved in the FL process, we propose to utilize an access class barring (ACB) method to select the uploading devices and formulate an optimization problem of the ACB factor. We also derive the expected asymptotic convergence rate of the proposed RAFL-MIMO scheme to analytically show that the proposed RAFL-MIMO scheme can improve the performance of FL. Simulation results based on${L2}$-norm linear regression, and MNIST handwritten digits identification, Cifar-10 photograph classification show that the proposed RAFL-MIMO scheme significantly outperforms the case of the RAFL-MIMO without the ACB factor.

Machine learning (ML) is a widely accepted means for supporting customized services for mobile devices and applications. Federated Learning (FL), which is a promising approach to implement machine learning while addressing data privacy concerns, typically involves a large number of wireless mobile devices to collect model training data. Under such circumstances, FL is expected to meet stringent training latency requirements in the face of limited resources such as demand for wireless bandwidth, power consumption, and computation constraints of participating devices. Due to practical considerations, FL selects a portion of devices to participate in the model training process at each iteration. Therefore, the tasks of efficient resource management and device selection will have a significant impact on the practical uses of FL. In this paper, we propose a spectrum allocation optimization mechanism for enhancing FL over a wireless mobile network. Specifically, the proposed spectrum allocation optimization mechanism minimizes the time delay of FL while considering the energy consumption of individual participating devices; thus ensuring that all the participating devices have sufficient resources to train their local models. In this connection, to ensure fast convergence of FL, a robust device selection is also proposed to help FL reach convergence swiftly, especially when the local datasets of the devices are not independent and identically distributed (non-iid). Experimental results show that (1) the proposed spectrum allocation optimization method optimizes time delay while satisfying the individual energy constraints; (2) the proposed device selection method enables FL to achieve the fastest convergence on non-iid datasets.

With the development of blockchain and communication techniques, the Metaverse is considered as a promising next-generation Internet paradigm, which enables the connection between reality and the virtual world. The key to rendering a virtual world is to provide users with immersive experiences and virtual avatars, which is based on virtual reality (VR) technology and high data transmission rate. However, current VR devices require intensive computation and communication, and users suffer from high delay while using wireless VR devices. To build the connection between reality and the virtual world with current technologies, mobile augmented reality (MAR) is a feasible alternative solution due to its cheaper communication and computation cost. This paper proposes an MAR-based connection model for the Metaverse, and proposes a communication resources allocation algorithm based on outer approximation (OA) to achieve the best utility. Simulation results show that our proposed algorithm is able to provide users with basic MAR services for the Metaverse, and outperforms the benchmark greedy algorithm.

Federated Learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. To balance the trade-off between energy and execution latency, and thus accommodate different demands and application scenarios, we formulate an optimization problem to minimize a weighted sum of total energy consumption and completion time through two weight parameters. The optimization variables include bandwidth, transmission power and CPU frequency of each device in the FL system, where all devices are linked to a base station and train a global model collaboratively. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, and CPU frequency for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm not only has better performance at different weight parameters (i.e., different demands) but also outperforms the state of the art.

A novel grant-free random access scheme with a high success rate is proposed to support massive access for machine-to-machine communications in massive multiple-input–multiple-output (MIMO) systems. This scheme allows active user equipments (UEs) to transmit their modulated uplink messages and super pilots consisting of multiple subpilots to a base station (BS). Then, the BS performs channel state information (CSI) estimation and uplink message decoding by utilizing a proposed graph combined clustering independent component analysis (GCICA) decoding algorithm and then employs the estimated CSIs to detect active UEs by using the characteristic of asymptotic favorable propagation of massive MIMO channel. We call this proposed scheme as the GCICA-based random access (GCICA-RA) scheme. We analyze the successful access probability, missed detection probability, and uplink throughput of the GCICA-RA scheme. Numerical results show that the GCICA-RA scheme significantly improves the successful access probability and uplink throughput, decreases missed detection probability, and provides low CSI estimation error at the same time.

Abstract A new random access scheme is proposed to solve the intra‐cell pilot collision for M2M communication in crowded asynchronous massive multiple‐input multiple‐output systems. The proposed scheme utilizes the proposed estimation method of signal parameters to estimate the effective timing offsets, and then active user equipments obtain their timing errors from the effective timing offsets for uplink message transmission. The mean squared error of the estimated effective timing offsets of user equipments and the uplink throughput are analysed. Simulation results show that, compared to the exiting random access scheme for the crowded asynchronous massive multiple‐input multiple‐output systems, the proposed scheme can improve the uplink throughput and estimate the effective timing offsets accurately at the same time.

Internet of Things (IoT) is able to provide various physical objects to exchange their information through the 6G wireless communication network. However, with the large increasing number of the IoT devices (IoDs), the deployment of IoDs faces two basic challenges, i.e., spectrum scarcity and energy limitation. Cooperative spectrum sharing and simultaneous wireless information and power transfer (SWIPT) provide effective ways to improve the spectrum and energy efficiency. In this article, two SWIPT cooperative spectrum sharing methods are proposed to improve the energy and spectrum efficiency for 6G-enabled cognitive IoT network, in which IoDs access to the primary spectrum by serving as orthogonal frequency-division multiplexing (OFDM) relay with the energy harvested from the received radio-frequency (RF) signal. Specifically, in phase1, the IoDs transmitter (DT) in the cognitive IoT network performs information decoding and energy harvesting with the received RF signal. In phase2, DT transmits the signals of the primary system and itself to the corresponding receiver by utilizing orthogonal subcarriers with the harvested energy to avoid the interference. Achievable rates of the cognitive IoT system with amplify-and-forward (AF) and decode-and-forward (DF) relaying mode are maximized through joint power and subcarrier optimization, while ensuring the target rate of the primary system. Simulation results are performed to illustrate the improvement of the spectrum and energy efficiency.

Reconfigurable intelligent surface (RIS), a recently introduced technology for future wireless communication systems, enhances the spectral and energy efficiency by intelligently adjusting the propagation conditions between base stations (BSs) and mobile equipments (MEs). An RIS consists of many low-cost passive reflecting elements that are optimized to improve the quality of the received signal. In this paper, we study the problem of power control at the BS and RIS optimization for application to physical-layer broadcasting. Our goal is to minimize the transmit power at the BS by jointly designing the transmit beamforming at the BS and the phase shifts of the passive elements at the RIS. Furthermore, to help validate the proposed optimization methods, we derive lower bounds to quantify the average transmit power at the BS as a function of the number of MEs, the number of RIS elements, and the number of antennas at the BS. The simulation results demonstrate that the average transmit power at the BS is close to the lower bound in an RIS-aided system, and is significantly lower than the average transmit power in conventional schemes without an RIS.

As a recently proposed idea for the future wireless systems, intelligent reflecting surface (IRS) can assist communications between entities which do not have high-quality direct channels in between. Specifically, an IRS comprises many low-cost passive elements, each of which reflects the incident signal by incurring a phase change so that the reflected signals add coherently at the receiver. In this paper, for an IRS-aided wireless network, we study the problem of power control at the base station (BS) for physical-layer broadcasting under quality of service constraints, by jointly designing the transmit beamforming at the BS and the phase shifts of the IRS units. Furthermore, we derive a lower bound of the minimum transmit power at the BS to validate the proposed optimization method. Simulation results show that, the transmit power at the BS approaches the lower bound with the increase of the number of IRS units, and is much lower than that of the communication system without the IRS.

A novel grant-free random access scheme is proposed to support massive connectivity with low access delay and overhead for machine-to-machine communication in massive multiple-input-multiple-output systems. This scheme allows all active user equipments (UEs) to transmit their pilots and uplink messages via the same time-frequency resource and performs the joint active UEs detection and uplink message decoding without channel estimation in one shot by utilizing the proposed ensemble independent component analysis (EICA) decoding algorithm. We call the proposed scheme the EICA-based pilot random access (EICA-PA). We analyze the successful access probability, probability of missed detection, and uplink throughput of the EICA-PA scheme. Numerical results show that the EICA-PA scheme significantly improves the successful access probability and uplink throughput, decreases missed detection probability and provides low-frame error rate at the same time.

Long Short-Term Memory (LSTM) network, a popular deep-learning model, is particularly useful for data with temporal correlation, such as texts, sequences, or time series data, thanks to its well-sought after recurrent network structures designed to capture temporal correlation. In this article, we propose to generalize LSTM to generic machine-learning tasks where data used for training do not have explicit temporal or sequential correlation. Our theme is to explore feature correlation in the original data and convert each instance into a synthetic sentence format by using a two-gram probabilistic language model. More specifically, for each instance represented in the original feature space, our conversion first seeks to horizontally align original features into a sequentially correlated feature vector, resembling to the letter coherence within a word. In addition, a vertical alignment is also carried out to create multiple time points and simulate word sequential order in a sentence (i.e.,word correlation). The two dimensional horizontal-and-vertical alignments not only ensure feature correlations are maximally utilized, but also preserve the original feature values in the new representation. As a result, LSTM model can be utilized to achieve good classification accuracy, even if the underlying data do not have temporal or sequential dependency. Experiments on 20 generic datasets show that applying LSTM to generic data can improve the classification accuracy, compared to conventional machine-learning methods. This research opens a new opportunity for LSTM deep learning to be broadly applied to generic machine-learning tasks.

Due to the massive number of devices in the M2M communication era, new challenges have been brought to the existing random-access (RA) mechanism, such as severe preamble collisions and resource block (RB) wastes. To address these problems, a novel sparse message passing (SMP) algorithm is proposed, based on a factor graph on which Bernoulli messages are updated. The SMP enables an accurate estimation on the activity of the devices and the identity of the preamble chosen by each active device. Aided by the estimation, the RB efficiency for the uplink data transmission can be improved, especially among the collided devices. In addition, an analytical tool is derived to analyze the iterative evolution and convergence of the SMP algorithm. Finally, numerical simulations are provided to verify the validity of our analytical results and the significant improvement of the proposed SMP on estimation error rate even when preamble collision occurs.

This paper proposes to enable deep learning for generic machine learning tasks. Our goal is to allow deep learning to be applied to data which are already represented in instance-feature tabular format for a better classification accuracy. Because deep learning relies on spatial/temporal correlation to learn new feature representation, our theme is to convert each instance of the original dataset into a synthetic matrix format to take the full advantage of the feature learning power of deep learning methods. To maximize the correlation of the matrix, we use 0/1 optimization to reorder features such that the ones with strong correlations are adjacent to each other. By using a two dimensional feature reordering, we are able to create a synthetic matrix, as an image, to represent each instance. Because the synthetic image preserves the original feature values and data correlation, existing deep learning algorithms, such as convolutional neural networks (CNN), can be applied to learn effective features for classification. Our experiments on 20 generic datasets, using CNN as the deep learning classifier, confirm that enabling deep learning to generic datasets has clear performance gain, compared to generic machine learning methods. In addition, the proposed method consistently outperforms simple baselines of using CNN for generic dataset. As a result, our research allows deep learning to be broadly applied to generic datasets for learning and classification (Algorithm source code is available at http://github.com/hhmzwc/EDLT).

To resolve the pilot contamination problem in the massive multiple-input multiple-output (MIMO) systems, a pilot random access scheme which combines the strongest user collision resolution with timing advance information (SUCR-TA), is proposed. This scheme takes the propagation delay into account, and selects an appropriate TA information for each active pilot to reduce the number of contenders who will perform the SUCR algorithm. We also analyze the system throughput of the SUCRTA scheme, i.e. the number of MTC devices that can be allocated pilots successfully. Simulation results demonstrate that, compared with the SUCR algorithm, SUCR-TA scheme can significantly improve the system throughput.

To resolve intra-cell pilot collision in crowded massive multiple-input multiple-output systems, a new pilot random access protocol, called strongest-user collision resolution combined graph-based pilots access (SUCR-GBPA), is proposed. This protocol allows all failed user equipments (UEs) to randomly select a pilot from the pilots that are not selected by any UE in the initial step. By exploiting the characteristic that the channel responses between UEs and the base station are invariant within the coherence time, a bipartite graph is established where active UEs and selected pilots are considered variable nodes and factor nodes, respectively. Based on this bipartite graph, the successive interference cancellation algorithm is employed to estimate the channel response of each UE. Finally, utilizing the and-or tree principle, we analyze the performance of the proposed SUCR-GBPA protocol, including the maximum number of the tolerable active UEs, the minimum number of the required pilots, uplink throughput, and the mean-square-error performance of the SUCR-GBPA channel estimation. Simulation results demonstrate that, compared with the SUCR protocol, the proposed SUCR-GBPA protocol significantly improves the uplink throughput and provides accurate estimation on the channel response at the same time.