In massive multiple-input multiple-output (MIMO) systems, the channel state information (CSI) feedback enables performance gain in frequency division duplex networks. However, with the increase in the number of antennas, the feedback overhead of CSI will also enhance. To this end, this study addresses the issue of massive MIMO CSI reconstruction using convolutional neural network (CNN), long short-term memory (LSTM) and attention mechanism, and proposes an efficient network architecture (denoted as CNN-LSTM-A). To achieve a compromise between performance and complexity, the proposed method significantly reduces the number of training parameters by utilising a single-stage network rather than a multiple-stage network. Finally, simulation results show that the authors method can reduce the feedback overhead of CSI effectively, and achieves better performance in terms of CSI compression and recovery accuracy compared with existing state-of-the-art methods.

Device-to-device (D2D) communication plays a significant role in cellular networks as it can increase the capacity, spectrum efficiency and energy efficiency of the system. However, the large computational complexity of D2D resource management optimisation algorithms creates a serious gap between theoretical design and real-time processing, which leads to the limited use of D2D communication technology. In this study, a novel deep learning-based optimisation method is proposed to overcome the high computational complexity of joint beamforming design and power allocation optimisation algorithms in D2D communication. Unlike existing approaches, the authors design a convolutional neural network based end-to-end network structure to solve complex computing problems for channel state information under a limited feedback scenario. The Max-SE loss function which indicates quality-of-service (QoS) constraint and interference constraint, together with the mean squared error (MSE) function, are designed to maximise the spectral efficiency of the system while minimising the total transmit power. The simulation results show that the proposed approach can achieve performance comparable to the weighted minimum MSE scheme with low computation time.

In this study, the authors consider the application of machine learning (ML) models in cooperative spectrum sensing of cognitive radio networks (CRNs). Based on a statistical analysis of the classic energy detection scheme, the probability of detection and false alarm is derived, which depends solely on the number of samples and signal-to-noise ratio of the secondary users. The channel occupancy detection obtained from the established analytical techniques such as maximum ratio combining and AND/OR rules is compared to different ML techniques, including multilayer perceptron (MLP), support vector machine, and Naive Bayes, based on receiver operating characteristic and area under the curve metrics. By using standard profiling tools, they obtain the computational performance of the analysed models during the training phase, a critical step for operating in CRNs. Ultimately, the results demonstrate that the MLP ML technique presents a better trade-off between training time and channel detection performance.

In this study, the authors review various jamming and anti-jamming strategies in the context of cognitive radios (CRs). The study explores different jamming models and classifies them according to their functionality. Furthermore, a study of jamming detection techniques is provided to enable a CR to identify different jamming signals. Finally, anti-jamming communications are discussed in detail to encounter different types of jamming attacks. The focus of the study is on advanced anti-jamming approaches that are based on learning strategies including, for example, game theoretic learning, reinforcement learning and deep learning. They show differences and similarities between these approaches and the conditions under which each of the algorithms can be useful.

Cognitive radio networks (CRNs) are vulnerable to spoofing attacks due to their wireless and cognitive nature. Since the traditional cryptographic authentication can hardly prevent such attacks in CRNs, the physical-layer authentication has been investigated for recent years. To achieve a light-weight physical-layer authentication, a rollout partially observable Markov decision process-based algorithm, named RoPOMDP, is proposed in this study. In general, RoPOMDP formulates the physical-layer authentication as a zero-sum game, based on which a hypothesis test upon channel vectors is developed. That allows us to design the gains for both spoofers and receivers based on Bayesian risks for the game, in which the spoofing attack probability is predicted by a non-linear function approximation utilising v-support vector regression. Then, a RoPOMDP is employed to estimate the optimal threshold for the test statistic such that spoofing attacks can be detected. The theoretical analysis and simulations indicate that: (i) RoPOMDP improves the spoofing detection accuracy; (ii) as a light-weight algorithm, the complexity of RoPOMDP is lower than contemporary ones.

Physical layer (PHY) security is an important issue in wireless communication systems. In this study, the authors investigate the interactions between the PHY security performance and the spectrum access technique in a cooperative cognitive radio (CR) network. In the classical spectrum access, if the measured energy on a given subchannel is less than a threshold, the subband is dedicated for CR transmission. Here, they consider a probabilistic spectrum access (PSA), which assigns to each primary subchannel a probability which is determined according to the measured energy on that subchannel. In addition, both spectrum access and CR power allocation are performed simultaneously. They formulate the general outage probability and some important PHY security performance metrics, such as average secrecy rate, secrecy outage probability, and probability of positive secrecy rate in terms of the spectrum access and optimal power allocation functions. The authors' numerical analysis indicates that the PSA method achieves a superior PHY security and outage performance compared to the classical threshold-based spectrum sensing and power allocation method.

In a multi-user cognitive radio network (CRN), mobile or hidden secondary users (SUs) are present. Conventionally, such SUs utilize rigid threshold value (λ) for spectrum sensing (SS). When these SUs perform SS, they receive poor quality signals from primary users. This provokes erratic SS decisions, reduces the involvement of SUs in SS, diminishes the probability of detection (P _d) and raises miss detection (P _m) or false alarm of SUs. As a consequence of this, SUs are not able to participate in SS and allocation in emergency circumstances. To alleviate these problems, an adaptive λ can be utilized for mobile/hidden SUs during SS. Thus, a two-level λ optimization technique for SS has been proposed using a coalition formation approach to maintain co-operation among SUs. The proposed technique has been validated on Universal Software Radio Peripheral test-bed. Estimation of the probability of error (P _e), P _d, and P _m for mobile/hidden SUs with energy detection SS (EDSS) performed using a fixed λ and the two-level optimized λ. From these estimations, it has been observed that compared to the fixed λ EDSS, P _e and P _m is reduced remarkably, and P _d is enhanced for mobile/hidden SUs using the two-level optimized λ EDSS.

In this study, a new network architecture based on the software-defined networking (SDN) approach is proposed for cognitive radio networks (CRNs). The proposed network architecture [software-defined cognitive radio (SDCR)] assumes the responsibilities of network resource management for CRNs and provides a dynamic spectrum management mechanism with an SDN controller. In this way, the dependency of network users on base stations is reduced in dynamic cognitive radio environments, and network performance is improved by delegating some of the management responsibilities to the controller. The performance analysis of the SDCR is carried out through the RIVERBED MODELER simulation software. End-to-end delays and packet loss rates for the primary network are investigated by selecting different offered loads for secondary users. In addition, for the equal and different packet sizes, primary network and SDCR throughput are examined and network performance is improved by using channel bonding technique. The results indicate that the SDCR outperforms the traditional CRN architecture, in terms of the throughput, and the proposed architecture can provide effective performance. Bit error rate parameter is investigated in the study and the energy consumption parameter of the SDCR is also compared with the cognitive radio wireless network.

Emerging cellular-enabled unmanned aerial vehicles (UAVs) communication poses both opportunities and challenges to the current research of UAV applications. On the one hand, the advanced cellular technologies and authentication mechanisms make significant performance improvements of reliability, security, coverage, and throughput of UAVs possible. On the other hand, the considerably dynamic characteristics of the new aerial users bring some complicated and open issues to the future heterogeneous network. To throw some light on this field, the authors study the joint power allocation and channel reuse problem of uplink transmission in a cellular-enabled UAVs network with full consideration of the rapid channel variations resulting from high mobility of UAVs. Given the diverse requirements of terrestrial cellular users (CUs) and UAVs, i.e. large capacity for CU links and ultra-reliability for UAV links, they formulate the problem as optimising the uplink capacities of CUs with reliable transmission constraint of UAVs. By decoupling the intricate problem into two sub-problems, a joint resource allocation algorithm is proposed, which relies only on the statistical information of dynamic channels to implement, hence is robust. Finally, numerical results are provided to corroborate the anticipated performances of the proposed scheme.

Geometric stochastic method and deterministic ray tracing method are two common methods of modelling massive multiple-input multiple-output (MIMO) channels. The former has high computational efficiency but a large number of input parameters need to be extracted from measurements for different environments. Conversely, the latter is more suitable for a specific environment but consumes a lot of computing costs. In this study, a novel three-dimensional (3D) deterministic ray tracing method for massive MIMO channel modelling is proposed. The computational efficiency can be improved in two aspects compared with conventional deterministic ray tracing methods. Firstly, substantial intersection tests used in determining the propagation paths of rays are replaced with the adjacency relationships between tetrahedrons. Secondly, the process of ray tracing is independent of the location of a receiving antenna and therefore repeated ray tracing process is unnecessary for different elements of receiving antenna array. The proposed method is also used as a substitute for measurements to extract input parameters for geometric stochastic channel models. The accuracy of the proposed method in massive MIMO channel modelling and parameters extraction is verified by comparing the results with measurements and other existing channel models.

In this study, a new transmitter–receiver approach for high-speed train (HST) downlink orthogonal frequency division multiplexing (OFDM) data transmission and detection in fifth generation (5G) communication systems is proposed. The proposed method uses a new Doppler shift frequency (DSF) estimation method, proposed in this study, to calculate the channel tap DSFs at the HST receiver. These estimated DSFs are used to calculate the channel taps’ angle of departure (AoD). Using the projected AoDs, the transmitter beamformer adjusts its coefficients to suppress the non-line-of-sight (NLoS) channel taps and a DSF compensation block is used to mitigate the line-of-sight channel tap DSF. Simulation results indicate the fidelity of the proposed DSF estimation method and the proposed transmitter–receiver approach. Due to the accuracy of the proposed DSF estimation method and the effectiveness of the beamformer in suppressing the NLoS channel taps, the approach of using a classic digital modulation and demodulation method instead of the OFDM scheme is appraised. Simulation results indicate that this shift from the OFDM modulation to the classic modulation results in a data detection approach which has acceptable accuracy, low computational complexity, and high spectral efficiency.

Localisation is one of the most important services in sensor networks. The impact of the used localisation technique used reflects on wireless sensor network services such as coverage or event detection. Accuracy is considered to be one of the factors that is related to successful network performance in most sensor network applications. Communication ranging is one of the practical applicable technique for localisation on short-range communication nodes with no additional components. This study proposes an enhanced communication ranging localisation technique with high accuracy. The authors evaluated and validated the proposed technique in a forest environment using 20 Waspmote Nodes and Meshlium router (Spanish product). The novelty of the proposed localisation technique is based on controlling communication range by manipulating the XBee transmitter power changing ability on four rounds to provide the best-predicted location. The results demonstrated the locations of nodes were found with error range between 0 and 22 m. The network location error decreased starting with 30 m in round 1 down to 8 m in round 4. The technique can be applied to different types of networks and technologies as long as the transmission power can be set to different values and the communication range is known or can be measured manually.

Error performance of hybrid subcarrier intensity modulation (hybrid-SIM) in optical free-space satellite downlink has been studied in this work. Bit error rate (BER) is improved by aperture averaging and spatial receiver diversity and it is found out be effective in strong turbulence regime. Subsequently, the reduction in scintillation index has been investigated by implementing a single large receiver and an array of point receivers of length with the same effective aperture area. Moreover, the BER at different turbulence conditions is compared with minimum shift keying and multiple levels of pulse position modulation pertaining to aperture averaging. Upon analysing the single input multiple outputs (SIMO) system, the desired response is obtained above a certain threshold in average received irradiance. At different zenith angles and turbulence strengths for , the threshold is 4.59 and 3.35 dB, respectively, and it rises by 13.6 and 26.43 dB when is increased to 9. This constraint can be exploited to optimise the number of receivers concerning system requirement and availability. Further, the pointing error effects are also investigated for SISO and SIMO systems, which takes into account both atmospheric turbulence and misalignment induced fading.

In infrastructure-less scenarios such as rural environments, wild emergency response, military applications and disaster relief, unmanned aerial vehicles (UAVs) are capable of providing enhanced mobile edge computing (MEC) services for ground users. Although small latency is the most important advantage of MEC system, how to provide delay aware scheduling in UAV-enabled MEC system still remains unsolved. In this study, the authors investigate the delay aware scheduling problem in UAV-enabled orthogonal frequency division multiple access (OFDMA) MEC system and formulate two non-convex optimisation problems. Moreover, they consider uplink and downlink architecture with characteristics in different UAV-ground links and traffic load. Furthermore, they propose two novel multi-stages resource allocation algorithms, i.e. the JSPA-T and JSPA-F algorithms with respect to downlink transmit power allocation and sub-carrier assignment. The mathematical frameworks with duality theory based alternative search optimisation and successive approximation method are proposed. The simulation results validate the performance improvement of the proposed solutions as well as the fast converge behaviour and small computational complexity.

In this study, elliptic curve cryptography (ECC) is elected for tenant authentication, data encryption, and data decryption due to its minimum key size. The proposed ECC-based authentication approach allows the authorised person to access private data; it protects different related attacks effectively. To develop more secure data encryption, the authors have combined a nature-inspired optimisation, such as a moth search algorithm (MSA) with ECC, to select the correct and optimal value of the elliptic curve. The proposed encryption and decryption approach combines DNA encoding with the ECC encryption algorithm. The mechanism of DNA encoded ECC provided multi-level security with less computational power. The security analysis of the proposed method has been provided to prove its effectiveness against certain attacks, such as denial-of-service attack, impersonation attack, reply attack, plaintext attack and chosen-ciphertext attack. The experimental result is evaluated based on encryption time, decryption time, throughput and key size of the security model. The average execution time of the proposed encryption and decryption is only 83.153 and 86.076 s, respectively. From the evaluation, it is clearly determined that the proposed technique provides two-layer security with minimum key size and less storage space.

Cellular systems present one of the most suitable wireless technologies to efficiently serve critical machine-type communications (MTC) that require strict quality-of-service (QoS) guarantees. Therefore, ultra-reliable and low-latency communications is a target use case in the design of the upcoming generations of cellular networks. From the radio resource management perspective, guaranteeing such stringent QoS requirements in long term evolution (LTE) networks is a challenging task, especially in the case of the coexistence of MTC with the human-type communications (HTC). In this study, the authors address the resource allocation and scheduling problem of critical MTC that coexist with HTC in LTE. The optimisation problem is formulated such that the overall system utility is maximised while fulfilling the different QoS demands of the two sets of users. Utilising the effective bandwidth and effective capacity theories, a cross-layer design is developed to guarantee the QoS requirements of the critical MTC. For a computationally-efficient solution of the problem, they formulate it as a two-sided matching process that can be used as a practical scheduling scheme. To this end, they analyse the convergence, stability, and computational complexity of the proposed methods. Results reveal the close-to-optimal performance of the matching-based scheduling scheme and its superiority to other existing techniques.

Here the intelligent jammer issue is studied. With the rapid development of cognitive radio technology, current cognitive terminals can adaptively or intelligently switch channel by spectrum sensing and decision-making. Most of the traditional jamming methods, such as swept jamming and comb jamming, generally work in a relatively fixed pattern, which are not able to effectively jam the terminals empowered with cognition and spectrum decision-making capability. In view of this problem, the authors propose an intelligent jamming decision-making system based on reinforcement learning. First, in order to jam a pair of transmitter and receiver with adaptive frequency hopping capability, a jammer with spectrum sensing, offline training and learning scheme is proposed. Second, a reinforcement learning-based algorithm for jamming decision-making is proposed and simulated. A special feature of the proposed scheme is that considering the reward is difficult to obtain in the actual communication system, a virtual jamming decision-making method is used to enable the jammer to learn and jam efficiently without the user's prior information. Finally, the proposed jamming model and algorithm are implemented and verified on Universal software radio peripheral testbed.

IEEE concentrates on the development of effective media independent handover (IEEE 802.21 MIH) services. The major aim of IEEE 802.21 MIH is to optimise the handover process to make an uninterrupted handover service with less delay. The handover process is categorised into two types a horizontal and vertical process. Among them, vertical handover (VH) needs parameter optimisation for better performance. The optimised result depends on the parameter selection to avoid the rate of handover failure. Although the availability of various optimisation procedures for VH management, many existing works consider one/two parameters for VH optimisation. So that resultant optimal handover solution will not be better in terms of failure rate, latency, and accuracy. Thus, a method of multi-objective emperor penguin handover optimisation (MOEPHO) is developed in the proposed work, which includes almost overall network parameters for VH optimisation. So that, accurate handover with less delay and the minimum energy consumption is achieved in this work. Network simulator 2 working platform is used for the research evaluation. The resultant performances are compared with whale optimisation algorithm-based neural network, adaptive cross-layer design, fuzzy intelligent decision making and novel type 2-fuzzy logic controller to show the effectiveness of MOEPHO.

The next generation of mobile communication systems is being developed for high-bandwidth mobile networks to accommodate applications with high data rates and low delay requirements such as voice over internet protocol, video streaming, cyber-physical systems and gaming. These applications consume a considerable amount of energy and hence drain the user equipment (UE) battery quickly. Long-term evolution (LTE)/LTE-advanced has adopted a discontinuous reception (DRX) mechanism to improve the energy efficiency of the UE. DRX allows UEs to monitor the physical downlink control channel in a discontinuous manner when there is no downlink traffic to reduce energy consumption. However, DRX results in higher latency due to its sleep cycle. In this study, the authors present a new scheme that improves energy efficiency in UE while maintaining an average packet delay around a permissible delay threshold. Numerical analysis and system simulation show that this scheme can achieve a significant power saving.

In this study, the authors study binary decision fusion over a shared Rayleigh fading channel with multiple antennas at the decision fusion centre (DFC) in wireless sensor networks. Three fusion rules are derived for the DFC in the case of distributed M-ary hypothesis testing, where M is the number of hypothesis to be classified. Namely, the optimum maximum a posteriori (MAP) rule, the augmented quadratic discriminant analysis (A-QDA) rule and MAP observation bound. A comparative simulation study is carried out between the proposed fusion rules in-terms of detection performance and receiver operating characteristic (ROC) curves, where several parameters are taken into account such as the number of antennas, number of local detectors, number of hypothesis and signal-to-noise ratio. Simulation results show that the optimum (MAP) rule has better detection performance than A-QDA rule. In addition, increasing the number of antennas will improve the detection performance up to a saturation level, while increasing the number of the hypothesis will deteriorate the detection performance.

For original partial transmit sequence (O-PTS), the conjugate operations can be applied to achieve the purpose of ameliorating the peak-to-average power ratio (PAPR) performance. But in this way, an observation has been found that some of these candidate signals has the same PAPR value that brings about great redundant computations. Based on this, a low-complexity PTS is put forward to abate the PAPR of orthogonal frequency division multiplexing (OFDM) systems, thereby avoiding redundant candidate signals. In proposed scheme, a novel scheme employing conjugate operations for generating candidate signals with different PAPR values is given, which avoids the generation of candidate signals with the same PAPR value and saves the needless computations. Meanwhile, the grouping is involved for further reduction in computational complexity. Simulation results illustrate that our scheme has the similar or superior PAPR performance with the remarkable reduction in computational complexity by comparison with O-PTS.

As an important positioning source of indoor positioning technology, Wi-Fi signals have attracted the attention of researchers for a long time. Fingerprint positioning can solve the problems caused by non-line-of-sight propagation and multipath effects. To improve the accuracy of Wi-Fi indoor positioning, this study proposes an indoor positioning algorithm based on fine-grained channel state information (CSI) and convolutional neural network (CNN). CSI is a kind of observable measurement that better describes the nature of Wi-Fi signal propagation than received signal strength indication. This method uses the subcarrier amplitude and phase difference information extracted from CSI data to establish fingerprints. The clustering method is used to analyse the number of clusters of fingerprint data, and the fingerprint database is divided into two sub-databases according to the threshold. CNNs with the same network structure are used to train the two kinds of fingerprint sub-databases. In the positioning stage, the sub-database to which the data to be measured belongs is determined according to the calibration algorithm, and the corresponding CNN model is used to estimate the position. Experiments are performed in a typical indoor environment. Compared with existing fingerprint-based positioning methods, this method has higher positioning accuracy.

Most nodes of Mine Internet of Things (Mine IoT) are powered by batteries, and wireless charging using mobile chargers (MCs) is an effective way to make nodes work sustainably. A novel hybrid charging method combining the controlled and opportunistic MCs (C&O charging) is proposed in this study. Workers (such as the repairmen and gas inspectors) carrying portable chargers are proposed to be opportunistic MCs to provide an incidental charging service for the surrounding rechargeable Mine IoT nodes while doing its own work to reduce the payload of controlled MCs. The hybrid charging model based on the incidental charging ability of the opportunistic MC is constructed and the scheduling strategy of the controlled MC and the queueing management scheme of the charging request are also proposed. The simulation results indicate that the power demands of the majority of the nodes in the maintenance areas can be met or partially met by opportunistic MCs and the charging time of C&O charging is greatly decreased compared to that of only using controlled MCs.

Information and communication technology (ICT) is one of the sectors that have the highest energy consumption worldwide. It implies that the use of energy in the ICT must be controlled. A software-defined network (SDN) is a new technology in computer networking. It separates the control and data planes to make networks more programmable and flexible. To obtain maximum scalability and robustness, load balancing is essential. The SDN controller has full knowledge of the network. It can perform load balancing efficiently. Link congestion causes some problems such as long transmission delay and increased queueing time. To overcome this obstacle, the link load balancing strategy is useful. The link load-balancing problem has the nature of NP-complete; therefore, it can be solved using a meta-heuristic approach. In this study, a novel energy-aware dynamic routing method is proposed to solve the link load-balancing problem while reducing power consumption using the multi-objective artificial bee colony algorithm and genetic operators. The simulation results have shown that the proposed scheme has improved packet loss rate, round trip time and jitter metrics compared with the basic ant colony, genetic-ant colony optimisation, and round-robin methods. Moreover, it has reduced energy consumption.

Free space optical (FSO) communication channels are affected by fluctuations in irradiance due to atmospheric turbulence and pointing errors. Recently, a generalized statistical model knows as Málaga () was developed to describe irradiance fluctuations of the beam propagating through a turbulent medium. In this paper, an approximate finite-series probability density function (PDF) for composite turbulence with pointing errors is verified. Considering multiple pulse-position-modulation (MPPM) with intensity modulation and direct detection, specific closed-form expressions for average symbol error rate (ASER) and outage probability are obtained. Moreover, asymptotic expressions for ASER and outage probability over the Málaga channel with pointing errors are presented. Finally, ASER and outage probability expressions are deduced in three turbulence regimes, strong, moderate, and weak. Therefore, simulation results are given to confirm the accuracy of the proposed expressions. The results show that the optimum beam divergence angle is 1 mrad for zero-boresight displacement and 2 mrad for nonzero-boresight at a distance of 1 km. By increasing the range to 5 km, atmospheric turbulence is found to have the dominant effect over boresight displacement. Moreover, the system performance at the optimized divergence angle is studied in terms of transmit power, normalized boresight, and link distance.