This article aims to improve spectrum efficiency (SE) for the unmanned aerial vehicle (UAV)-relayed cellular uplinks, through distinguishing both line-of-sight (LoS) and non-LoS (NLoS) links. Meanwhile, aiming to accommodate the air-to-ground (A2G) cooperative nonorthogonal multiple access (NOMA)-based cellular users (CUs) with a high energy efficiency (EE), a joint resource allocation (RA) problem is further considered for the UAV and the CUs. To solve the problem, first, an access-priority-based receiver determination (RD) method is derived. According to the RD result, the heuristic user association (UA) strategies are given. Then, based on the UA result, transmission powers of the CUs and the UAV are initialized based on their quality-of-service (QoS) demands. Furthermore, the subchannels are assigned to the associated CUs and the UAV with the reweighted message-passing algorithm. Finally, the transmission power of the CUs and the UAV is jointly fine-tuned with the proposed access control schemes. Compared with the traditional orthogonal frequency-division multiple access (OFDMA) scheme and the traditional ground-to-ground (G2G) NOMA scheme, simulation results confirm that the UAV-aided NOMA with the proposed joint RA scheme yields better performances in terms of the SE, the EE, and the access ratio of the CUs.

In this article, we introduce Wireless 2.0, the future generation of wireless communication networks, in which the radio environment becomes controllable and intelligent by leveraging the emerging technologies of reconfigurable metasurfaces (RMSs) and artificial intelligence (AI). In particular, we emphasize AI-based computational methods and commence with an overview of the concept of intelligent radio environments (IREs) based on RMSs. Then, we elaborate on data management aspects, the requirements of supervised learning by examples, and the paradigm of reinforcement learning to learn by acting. Finally, we highlight numerous open challenges and research directions.

Modulation signal classification (MSC) is an indispensable technique to make the possible applications of non-cooperative communications. Currently, convolutional neural network (CNN) based MSC techniques can achieve an outstanding performance at a fixed noise regime. However, they are hard to generalize to all of noise scenarios. Because these conventional methods are trained on specific signal samples with fixed SNR and they only perform well under corresponding noise condition. Unlike the conventional methods, in this paper, we propose a robust CNN based generalized MSC (GMSC) method with powerful generality capability. This capability stems from the mixed dataset, containing in-phase and quadrature (IQ) samples under various SNR regimes. Experimental results show that the proposed method is robust under varying noise conditions, while merely losing a slight performance with comparing with conventional methods.

Nonorthogonal multiple access (NOMA) significantly improves the connectivity opportunities and enhances the spectrum efficiency (SE) in the fifth generation and beyond (B5G) wireless communications. Meanwhile, emerging B5G services demand for higher SE in the NOMA-based wireless communications. However, traditional ground-to-ground (G2G) communications are hard to satisfy these demands, especially for the cellular uplinks. To solve these challenges, this article proposes a multiple unmanned-aerial-vehicles (UAVs)-aided uplink NOMA method. In detail, multiple hovering UAVs relay data for a half of ground users (GUs) and share the spectrums with the other GUs that communicate with the base station (BS) directly. Furthermore, this article proposes a K-means clustering-based UAV deployment scheme and location-based user pairing (UP) scheme to optimize the transceiver association for the multiple UAVs-aided NOMA uplinks. Finally, a sum power minimization-based resource allocation problem is formulated with the lowest Quality-of-Service (QoS) constraints. We solve it with the message-passing algorithm and evaluate the superior performances of the proposed scheduling and paring schemes on SE and energy efficiency (EE). Extensive simulations are conducted to compare the performances of the proposed schemes with those of the single UAV-aided NOMA uplinks, G2G-based NOMA uplinks, and the proposed multiple UAVs-aided uplinks with a facility location framework-based UAV deployment. Simulation results demonstrate that the proposed multiple UAVs deployment and UP-based NOMA scheme significantly improves the EE and the SE of the cellular uplinks at the cost of only a little relaying power consumption of UAVs.

Automatic modulation classification (AMC) is one of the most critical technologies for non-cooperative communication systems. Recently, deep learning (DL) based AMC (DL-AMC) methods have attracted significant attention due to their preferable performance. However, the study of most of DL-AMC methods are concentrated in the single-input and single-output (SISO) systems, while there are only a few works on DL-based AMC methods in multiple-input and multiple-output (MIMO) systems. Therefore, we propose in this work a convolutional neural network (CNN) based zero-forcing (ZF) equalization AMC (CNN/ZF-AMC) method for MIMO systems. Simulation results demonstrate that the CNN/ZF-AMC method achieves better performance than the artificial neural network (ANN) with high order cumulants (HOC)-based AMC method under the condition of the perfect channel state information (CSI). Moreover, we also explore the impact of the imperfect CSI on the performance of the CNN/ZF-AMC method. Simulation results demonstrated that the classification performance is not only influenced by the imperfect CSI, but also associated with the number of the transmit and receive antennas.

The fifth generation (5G) of wireless communications has led to many advancements in technologies such as large and distributed antenna arrays, ultra-dense networks, software-based networks and network virtualization. However, the need for a higher level of automation to establish hyper-low latency, and hyper-high reliability for beyond 5G applications requires extensive research on machine learning with applications in wireless communications. Thereby, learning techniques will take a central stage in the sixth generation of wireless communications to cope up with the stringent application requirements. This paper studies the practical limitations of these learning methods in the context of resource management in a non-stationary radio environment. Based on the practical limitations we carefully design and propose supervised, unsupervised, and reinforcement learning models to support rate maximization objective under user mobility. We study the effects of practical systems such as latency and reliability on the rate maximization with deep learning models. For common testing in the non-stationary environment, we present a generic dataset generation method to benchmark across different learning models versus traditional optimal resource management solutions. Our results indicate that learning models have practical challenges related to training limiting their applications. These models need an environment-specific design to reach the accuracy of an optimal algorithm. Such an approach is practically not realistic due to the high resource requirement needed for frequent retraining.

In fifth generation and beyond Internet of things (5G-IoT), the buffer-aided relaying network provide an efficient way to maintain the coverage area and enhance the edge user’s transmission experience. However, the effect of non-ideal factor to the buffer-aided relaying network, such as the signaling overhead, have not been investigated. In this paper, we propose a practical hybrid bit-level network coding (BNC) for the buffer-aided relaying network while taking the unreliable transmission, limited relay-buffer size and signaling overhead into consideration. Afterward, we derive its concise closed-form expressions and the associated upper bound expressions for the throughput, queuing delay and overflow probability. Monte-Carlo simulation proves the validness of our analysis. Simulation results also demonstrate that compared to existing studies, our proposal can enhance the system energy efficiency (EE) performance, and buffer size has a positive effect on the EE performance.

With the development of smart cities, the demand for artificial intelligence (AI) based services grows exponentially. The existing works just focus on cloud- edge or edge-device cooperative AI which suffers low learning efficiency of AI, while edge-to-edge cooperative AI is still an unresolved issue. Moreover, the existing researches concentrate on the computation offloading of the AI-based task, ignoring that it is a brain-like task performing sophisticated processing to raw data, which leads to the high latency and low quality of the learning services. To address these challenges, this paper proposes an on-demand learning offloading mechanism for edge-to-edge cooperative AI. Firstly, the principle of the learning capability and its offloading are proposed for the formal description of the learning resources migration. Secondly, the proposed mechanism realizes the bilateral learning offloading utilizing edge-to-edge and cloud-edge collaborations to handle AI-based tasks with high learning efficiency and resource utilization rate. Moreover, we model the edge-to-edge learning offloading allocation based on the concatenation of deep neural network (DNN) subtasks and their heterogeneous requirement of learning resources. Simulation results indicate the rationality and efficiency of the proposed mechanism.

As the evolving communication standards would leverage on high data rates and low power consumption, future communication systems must be able to demonstrate these strengths. Space-time block codes (STBC) and quasi-orthogonal STBC (QO-STBC) including beamforming are multiple-input multiple output (MIMO) system design techniques used to improve data rates and reduce bit error ratio (BER). STBCs for larger antenna configurations use QO-STBC schemes which suffer from self-interference problems. The self-interference in QO-STBC systems diminishes the data rates and worsen the BER. In this study, we present three (3) methods of overcoming the self-interference problems in QO-STBC systems. We implement the interference-free QO-STBC systems with directional beamforming to improve the data rates and also reduce the BER. The results show significantly improved BER performance when the interferences are eliminated. An additional 3dB gain is achieved at 10-4 BER when the interference-free QO-STBCs are operated with directional beamforming. In terms of data rates, up to 6 bits/s at reasonably low power consumption are realized when the Hadamard-based QO-STBC is operated with directional beamforming.

This paper presents performance analysis of an adaptive peak cancellation (PC) method to reduce the high peak-to-average power ratio (PAPR) for OFDM systems, while keeping the out-of-band (OoB) power leakage as well as an in-band distortion power below the pre-determined level. In this work, the increase of adjacent leakage power ratio (ACLR) and error vector magnitude (EVM) are estimated recursively using the detected peak amplitude. We present analytical framework for OFDM-based systems with theoretical bit error rate (BER) representations and detection of optimum peak threshold based on predefined EVM and ACLR requirements. Moreover, the optimum peak detection threshold is selected based on theoretical design to maintain the pre-defined distortion level. Thus, their degradations are restricted below the pre-defined levels which correspond to target OoB radiation. We also discuss the practical design of peak-cancellation signal with target OoB radiation and in-band distortion through optimizing the windowing size of the PC signal. Numerical results show the improvements with respect to both achievable BER and PAPR with the PC method in eigen-beam space division multiplexing (E-SDM) systems under restriction of OoB power radiation. It can also be seen that the theoretical BER shows good agreements with simulation results.

In this paper, we investigate the energy-efficient resource allocation problem in an uplink non-orthogonal multiple access (NOMA) millimeter wave system, where the fully-connected-based sparse radio frequency chain antenna structure is applied at the base station (BS). To relieve the pilot overhead for channel estimation, we propose a codebook-based analog beam design scheme, which only requires to obtain the equivalent channel gain. On this basis, users belonging to the same analog beam are served via NOMA. Meanwhile, an advanced NOMA decoding scheme is proposed by exploiting the global information available at the BS. Under predefined minimum rate and maximum transmit power constraints for each user, we formulate a max-min user energy efficiency (EE) optimization problem by jointly optimizing the detection matrix at the BS and transmit power at the users. We first transform the original fractional objective function into a subtractive one. Then, we propose a two-loop iterative algorithm to solve the reformulated problem. Specifically, the inner loop updates the detection matrix and transmit power iteratively, while the outer loop adopts the bi-section method. Meanwhile, to decrease the complexity of the inner loop, we propose a zero-forcing (ZF)-based iterative algorithm, where the detection matrix is designed via the ZF technique. Finally, simulation results show that the proposed schemes obtain a better performance in terms of spectral efficiency and EE than the conventional schemes.

In this paper, we propose a two-dimensional pilot allocation scheme over frequency- and delay-time domains (2D-PFD) for channel estimation in massive multiple-input multiple-output (MIMO)/time division duplex (TDD) system, where two- dimensional pilot resources are simultaneously allocated to each user for their uplink channel estimation. We evaluate bit error rate (BER) performance of massive MIMO/TDD system using the 2D-PFD scheme by computer simulation in order to clarify the effectiveness of the proposed pilot allocation compared with single dimensional pilot allocation over either delay-time domain or frequency domain, respectively.

This paper presents a novel localization method for electric vehicles (EVs) charging through wireless power transmission (WPT). With the proposed technique, the wireless charging system can self-determine the most efficient coil to transmit power at the EV’s position based on the sensors activated by its wheels. To ensure optimal charging, our approach involves measurement of the transfer efficiency of individual transmission coil to determine the most efficient one to be used. This not only improves the charging performance but also minimizes energy losses by autonomously activating only the coils with the highest transfer efficiencies. The results show that with the proposed system, it is possible to detect the coil with maximum transmitting efficiency without the use of actual power transmission and comparison of the measured efficiency. This paper also proves that with the proposed charger set-up, the position of the receiver coil can be detected almost instantly, which indeed saves energy and boosts the charging time.

In this paper, we propose a self-deployment strategy for non-stationary wireless extenders, where both back-haul and front-haul links are optimized. We present an artificial intelligence (AI) case based reasoning (CBR) framework that enables self-deployment with learning the environment by means of sensing and perception. New actions, i.e., extender positions, are created by problem-specific optimization and semi-supervised learning that balance exploration and exploitation of the search space. An IEEE 802.11 standard compliant simulations are performed to evaluate the framework on a large scale and compare its performance against existing conventional coverage maximization approaches. Experimental evaluation is also performed in an enterprise environment to demonstrate the competence of the proposed AI-framework.

This article discusses technology and opportunities available to embrace artificial intelligence (AI) in the design of autonomous wireless systems. A vision is presented for knowledge-driven wireless operation by means of AI disciplines, such as sensing, reasoning, knowledge management, and active learning. The aim is to provide readers with the motivation and a general big data-independent AI methodology for autonomous agents in the context of self-organization in real time by unifying knowledge management with sensing, reasoning, and active learning. Differences between training-based methods for matching problems and training-free methods for environment-specific problems are highlighted. Finally, we conceptually introduce the functions of an autonomous agent with knowledge management.