Abstract The dual function radar and communication technology plays a crucial role in Internet of Vehicles. However, fewer studies have focused on optimizing the joint performance of sensing and communication in full‐duplex Internet of Vehicles while considering fairness. Therefore, this paper considers the scenario that the full‐duplex gNB employs dual function radar and communication technology to simultaneously achieve vehicle localization and communication with multiple half‐duplex vehicles. By leveraging a reasonable beamforming scheme to mitigate the residual self‐interference of the echo signal, an optimization problem that maximizing the joint performance metric of sensing and communication is formulated with limited power at the gNB. After problem transformation, a double descent iteration power allocation algorithm is proposed to solve the non‐convex optimization problem and the complexity of the algorithm is analysed. Simulation results demonstrate that the proposed algorithm converges and could fairly improve both the sensing and communication performance.

Deep-learning (DL)-based channel state information (CSI) feedback has the potential to improve the recovery accuracy and reduce the feedback overhead in massive multiple-input-multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. However, the length of input CSI and the number of feedback bits should be adjustable in different scenarios, which cannot be efficiently achieved by the existing CSI feedback models. Therefore, an adaptive bidirectional long short-term memory network (ABLNet) for CSI feedback is first designed to process various input CSI lengths, where the number of feedback bits is in proportion to the CSI length. Then, to realize a more flexible feedback bit number, a feedback bit control unit (FBCU) module is proposed to control the output length of feedback bits. Based on which, a target feedback performance can be adaptively achieved by a designed bit number adjusting (BNA) algorithm. Furthermore, a novel separate training approach is devised to solve the model protection problem that the user equipment and next-generation nodeB are from different manufacturers. Experiments demonstrate that the proposed ABLNet with FBCU can fit for different input CSI lengths and feedback bit numbers; the CSI feedback performance can be stabilized by the BNA algorithm; and the proposed separate training approach can maintain the feedback performance and reduce the complexity of the feedback model.

In 5G communication systems, massive multiple-input multiple-output (MIMO) technology could compensate for the severe path-loss of millimeter-wave by high-gain beams. However, the excessive overhead of beam measurement induces a significant challenge for practical systems. To reduce the measurement overhead and improve the accuracy of beam selection, deep learning (DL) is employed to predict the signal quality of all beam pairs by measuring a few selected beam pairs. The proposed beam prediction network is mainly composed of input module, residual module and multi-layer perceptron (MLP) module, therefore denoted as ReMBP net. After the preprocessing for the input signal quality of measured beam pairs, the designed residual module is adopted to extract the high-dimensional feature vector, then the signal quality of all beam pairs could be predicted by the designed MLP module. Moreover, to improve the generalization ability of the proposed ReMBP net for different communication environments, the input module with a flexible input size of signal quality data is designed. Experiment results indicate that a high-accuracy beam selection could be achieved with low overhead compared with other traditional artificial intelligence (AI) models.

Autonomous vehicles have attracted increasing interest in recent years and decision making is a critical task for autonomous driving. To improve both the efficiency and safety of autonomous driving in various traffic scenarios, the target vehicle needs to timely make rational driving decisions according to its historical driving state and environment state. Therefore, a driving model based on Conditional Generative Adversarial Networks (CGAN) is proposed to imitate human driving behavior, which can generate the mapping from the current state to the driving decision. The proposed model not only exploits the spatiotemporal relationship of the observable driving states by leveraging the Convolutional LSTM (ConvLSTM) network, but also learns the different weight values of hidden features by utilizing the self-attention mechanism. Simulation results indicate that the proposed model is capable of generating human-like driving decisions and outperforms other reference models based on real traffic data.

Autonomous driving technology is one of the research hotspots in recent years. The development of some basic technologies such as motor sensors, vehicle to everything (V2X) and high-definition map also provides more powerful technical support for autonomous driving. However, it remains a challenge to propose a common decision strategy for autonomous driving. Considering the scenario that the networks can cover various urban roads through road side units (RSUs), this paper proposes a two-satage autonomous driving decision strategy based on environmental awareness and asynchronous advantage actor critic (A3C) algorithm. The first stage proposes a preliminary common model with safety guarantee for all roads; based on which the second stage trains a unique model for each road in consideration of different road features. Simulation results indicate that the proposed strategy can ensure high safety performance and driving efficiency.

To improve both efficiency and safety of automatic driving in complex traffic scenarios, autonomous vehicles need to have the ability to predict the future trajectories of vehicles. The interaction among vehicles in real traffic scenarios makes the trajectory prediction of vehicles challenging. By utilizing the historical trajectory of the targeted vehicle and the surrounding environment information, this paper proposes a coupling LSTM model in order to effectively predict the future trajectories of vehicles. The proposed model predicts the observable motion intentions of vehicles, and builds grids for the targeted vehicles to extract the implied space and intention information of the neighboring vehicles. Experiment results verify the proposed model in contrast to other basic models in real traffic scenarios.

High-definition (HD) map transmission is considered as a key technology for automatic driving, which enables vehicles to obtain the precise road and surrounding environment information for further localization and navigation. Guaranteeing the huge requirement of HD map data, the objective of this paper is to reduce the power consumption of vehicular networks. By leveraging the mobile rule of vehicles, a collaborative vehicle to everything (V2X) transmission scheme is proposed for the HD map transmission. Numerical results indicate that the proposed scheme can satisfy the transmission rate requirement of HD map with low power consumption.

The broadcasting services of vehicles in both vehicular networks and unmanned aerial vehicle (UAV) networks can be seen as the typical applications of all‐to‐all (A2A) scenario. In order to achieve efficient information broadcasting in A2A scenarios, this study proposes a two‐stage resource allocation scheme. In the first stage, to improve the frequency spectrum reusability, the communication area is divided into as many non‐overlapping square regions as possible based on the reliability requirements and power constraints of the vehicles, where the nonadjacent square regions share the same frequency spectrum. In the second stage, the vehicles belonging to the same region broadcast information with distributed time division multiplexing, and an improved coded slotted ALOHA scheme is proposed based on full‐duplex, where each vehicle can detect whether its broadcasted information is successful. Thus, the number of retransmissions and collision probability can be reduced and therefore the system energy can be saved. Results indicate that the two‐stage resource allocation scheme significantly improves the resource reusability while guaranteeing the communication reliability.

We consider a system where a massive multiple-input multiple-output (MIMO) base station (BS) transmits information and energy to multiple energy harvesting receivers. Each receiver has no power source and needs to harvest sufficient energy in order to decode its message from the received signal. Under either the power splitting mode or the time switching mode at the receivers, we consider two design problems. One is to maximize the minimum transmission rate among all receivers and the other is to optimize the system energy efficiency (EE) through jointly designing the power allocation proportions at the BS and the power splitting (or time switching) factors at the receivers. The optimal solutions to these problems are obtained either in terms of closed-form expressions or efficient algorithms by leveraging the asymptotic channel orthogonality and hardening effects of massive MIMO. The simulation results indicate that the power splitting mode outperforms the time switching mode in terms of both the minimum transmission rate and the system EE.

In conventional schedule‐based wireless transmission system, frequent interactions between devices and access networks lead to significant signalling overhead, and thus limit the development of low‐latency applications. Contention‐based data transmission (CBDT) is widely used as a promising solution to address the above issues. In this study, the authors propose a detection‐based retransmission scheme for CBDT to further reduce the delay‐outage probability which cannot be avoided due to collision. In this scheme, each device simultaneously monitors the occupied resource blocks during data transmission. When a collision event is detected, the retransmission for this packet is determined without waiting for the acknowledgment message from the receiver. The reliability performance is significantly improved for low‐latency applications, since the possible retransmission times for each packet is increased within the limited transmission period. In addition, the impacts of imperfect detection on extra transmission load and packet loss are analysed in detail. The simulation and analytical results demonstrate that the detection‐based scheme significantly improves the reliability of CBDT.

By leveraging direct device-to-device interaction, LTE vehicle-to-vehicle (V2V) communication becomes a promising solution to meet the stringent requirements of vehicular communication. In this paper, we propose jointly optimizing the radio resource, power allocation, and modulation/coding schemes of the V2V communications, in order to guarantee the latency and reliability requirements of vehicular user equipments (VUEs) while maximizing the information rate of cellular user equipment (CUE). To ensure the solvability of this optimization problem, the packet latency constraint is first transformed into a data rate constraint based on random network analysis by adopting the Poisson distribution model for the packet arrival process of each VUE. Then, utilizing the Lagrange dual decomposition and binary search, a resource management algorithm is proposed to find the optimal solution of joint optimization problem with reasonable complexity. Simulation results show that the proposed radio resource management scheme can reduce the interference from V2V communication to CUEs and ensure the latency and reliability requirements of V2V communication.

The control–data separation architecture (CDSA) has been regarded as a promising solution to effectively manage the heterogeneous network (HetNet) in the fifth‐generation mobile communication systems. Thus, this study investigates the resource allocation problems in CDSA‐based HetNet. To meet various requirements of data transmission, the authors first present a new framework with flexible resource management and efficient traffic control. In this framework, the control–data transmission supported by macro cell evolved nodeB is time‐sensitive and continuous with high reliability. On the basis of it, a traffic‐aware resource allocation approach is proposed to improve the resource efficiency. Once the traffic‐congestion requirements of the pattern are satisfied with the minimum spectrum, the throughput of small cells is simultaneously maximised due to orthogonal spectrum between macro and small cells by using this approach. Moreover, the traffic‐congestion analytical result is elaborately derived in terms of current network state. Three adaptive resource allocation schemes for implementing this approach are also designed with different complexities. Numerical results validate the accuracy of the proposed analytical method, and also indicate that the traffic‐aware resource allocation approach is more efficient than the static one.

To improve the energy efficiency of multi‐cell massive multiple‐input–multiple‐output system while guaranteeing the information transmission quality, this study proposes a dual‐layer coordinated beamforming scheme. In the proposed scheme, the beamformer at each evolved node B (eNB) is divided into a cell‐layer beamformer and a user‐layer beamformer. The cell‐layer beamformer is used to mitigate inter‐cell interference (ICI) by exchanging long‐term channel state information (CSI) among eNBs. The user‐layer beamformer serves user according to the local real‐time CSI at each eNB. On the basis of the dual‐layer structure, the cell‐layer beamformers, the user‐layer beamformers, and power allocation are jointly optimised in order to minimise the total transmit power across all the eNBs subject to the signal‐to‐interference‐plus‐noise ratio requirements and single‐antenna power constraints. To make the original problem solvable, the ICI is replaced by its upper bound. Then, the problem is partitioned into two convex sub‐problems, and two iterative algorithms are proposed in order to find the sub‐optimal solution to the original optimisation problem. Simulation results show that the proposed scheme performs better than two reference schemes including the existing zero‐forcing scheme and coordinative multiple point schemes.

We consider a system where a source node communicates with a destination node with the assistance of a wireless energy-powered full-duplex relay node. The relay node splits its received signal into two components for energy harvesting and information decoding, respectively, and forwards the decoded information using a portion of the harvested energy. To maximize the end-to-end transmission rate, the power splitting factor and energy consumption proportion are jointly optimized for the relay with a single transmit antenna in the presence of self-interference. Furthermore, for the relay with multiple transmit antennas, a suboptimal relay beamformer is first designed and the power splitting factor and energy consumption proportion are then jointly optimized. Finally, the asymptotic transmission rate is analyzed with a large number of transmit antennas. Simulation results are provided to demonstrate that the proposed schemes offer significant rate gain compared with some typical reference schemes, irrespective of the residual self-interference level. Especially, by employing a large number of source or relay transmit antennas, the wireless energy-powered relay system is capable of cutting its energy consumption significantly.

Non-orthogonal multiple access (NOMA) is a promising technology for the fifth generation. However, the increasing number of multiplexed users brings two challenges. One is the computational complexity of existing grouping schemes increases rapidly. The other is the performance of multiplexed users deteriorates sharply. To deal with these challenges, we propose a novel multi-user grouping scheme with low-complexity to select several UEs for multiplexing. Moreover, a corresponding power allocation scheme is proposed to guarantee the performance of the multiplexed users. Simulation results show that the novel multi-user grouping scheme can reduce the computational complexity at the cost of user fairness in contrast to the full search method. Besides, the proposed power allocation scheme can improve the spectrum efficiency compared with the existing power allocation schemes in NOMA systems.

We consider a downlink massive MIMO system, where the base station simultaneously sends information and energy to information users and energy users, respectively. The aim is to maximize the minimum harvested energy among the energy users while meeting the rate requirements of information users. With perfect channel state information (CSI), the problem is solved by obtaining the asymptotically optimal power allocation of information users and the combination coefficients of the energy precoder. For the CSI estimation in time-division duplex systems, orthogonal pilot sequences are employed by information users during the uplink, and one common pilot sequence is shared by all energy users. It is shown that the energy-harvesting performance of such a shared pilot scheme is always better than that of the orthogonal pilot scheme. Further, exploiting the intercell interference in multicell systems, a joint precoder is proposed for cooperative energy transfer, for which both the centralized and distributed implementations are given. Results indicate that the cooperative energy transfer always outperforms the noncooperative scheme with either perfect or estimated CSI.

Compact structure of the large-scale antenna array and low power angular spread (PAS) in vertical dimension improve the fading correlation of wireless channel dramatically in full-dimension multiple input multiple output (FD-MIMO) systems. Whereby beamforming (BF) can fully exploit the quasi-static spatial correlation to reduce dependence on the instantaneous channel state information at the transmitter (CSIT) and simplify the complexity of signal process, but also incur a loss of system performance. In this paper, we analyze the potential of exploiting spatial correlation in FD-MIMO systems, and propose an interesting spatial-correlation-based partial-channel-aware beamforming (SP-BF) scheme. Through the rationale of Givens rotation, SP-BF leverages the CSIT of partial channels, i.e., reduced-dimension channel vector, to further boost the system performance achieved by exploiting the spatial correlation. By applying this scheme, FD-MIMO in frequency division duplex (FDD) systems, where no channel reciprocity could be exploited, can make a tradeoff between the system performance and the overhead of acquiring CSIT. In addition, we validate the proposed scheme by virtue of the Monte Carlo simulations.

This study comprehensively investigates the performance of the downlink massive multiple‐input multiple‐output (MIMO) system with channel state information (CSI) delay, when the base station serves multiple user terminals (UTs) taking advantage of maximum ratio transmission precoding. Through the characteristic analysis of the received signal‐to‐interference‐plus‐noise ratio at UT, the tight lower bound of average area spectrum efficiency (SE) and its asymptotic bound with the infinite number of UTs are deduced, respectively. Based on the asymptotic bound and the realistic power consumption model consisting of both radiated power and circuit power, the trade‐off between SE and energy efficiency (EE) is developed, and the optimal EE with respect to SE is attained concisely. Moreover, the approximate expressions of both outage probability and bit error ratio (BER) are derived when the massive MIMO system works at its interference limited region. All theoretical results coincide to numerical results, and they show that deploying more transmission antennas will be helpful to improve SE, EE and reliability simultaneously; SE will be enhanced; however, the reliability, including both outage probability and BER, will be worsened by multiplexing more UTs; enlarging CSI delay can extensively deteriorate SE, EE and reliability.

Massive multiple-input multiple-output (MIMO) has been seen as a promising technology to improve the spectrum efficiency (SE), reliability and energy efficiency (EE) for the next generation wireless communication systems. Excessive energy consumption of wireless communication networks induces both the increasing carbon emission and unaffordable operational expenditure in recent years. In this paper, energy efficient power allocation scheme is investigated for the massive MIMO system with the maximum ratio transmission (MRT) precoding, since MRT precoding can balance the system performance and complexity. As of the intractable expression of the received SINR at user terminal (UT), an approximate expression is deduced by proper simplification. Based on the simplified expression, a power allocation algorithm is proposed to achieve the optimal EE according to convex optimization theory. Compared with the power allocation scheme ignoring the inter user interference, the proposed power allocation algorithm can enhance EE and decrease transmission power, and does not impair the SE. Simulation results also show that both the EE and SE are improved by increasing the number of antennas at BS and the number of multiple UTs.

Green communications is put forward to decrease the operational expenditure (OpEx) and carbon emission of communication networks in recent years. The relationship between spectrum efficiency (SE) and energy efficiency (EE) has induced more attentions in academic field, however, most efforts are spent on SE-EE trade-off of link-level not system-level. In this paper, we analyze the trade-off between average area SE (A2SE) and EE under the realistic power consumption model (PCM) in system-level perspective. First, we give the theoretical closed-form expression of A2SE for a cell as a function of edge SNR. And then, closed-form approximation (CFA) of A2SE is derived, and it largely coincides with theoretical A2SE and is reversible. Based on the CFA, we find the closed-form trade-off of A2SEEE concisely. Further, the optimal EE, corresponding A2SE and transmission power of BS under different cell radiuses are got according to the A2SE-EE trade-off. These results are helpful to design cell radius and transmission power which meet different needs for A2SE and EE of wireless networks.

With the tremendous growth in wireless networks market, unprecedented energy consumption and emissions of carbon dioxide (CO2) is a growing concern for both operators and governments. OFDM technology has been adopted by many standards organizations due to its high spectrum efficiency, but induces poor energy efficiency of power amplifier (PA). A new scheme named Selecting Sub-Carriers Modulation (SSCM) to lower the input power of PA is given in this paper. SSCM divides the information bits into two parts of bits according to modulation mode: the first part of bits selects some sub-carriers of OFDM to transmit nothing, another part of bits is transmitted by the remainder sub-carriers. Sub-carriers transmitting nothing do not need energy, and fewer number of sub-carriers transmitting modulation symbols can improve PA's efficiency because of the lower peak-to-average power ratio (PAPR). Analysis results show SSCM with different modulation modes can lower input power of PA with different proportion compared with traditional OFDM. Theoretical analysis and simulation results of the reliability of SSCM are given and match closely. In multi-path channel, SSCM with BPSK has the same performance as BPSK in traditional OFDM, while SSCM with QPSK performs worse than QPSK in traditional OFDM.