Search

This paper proposes a novel bit loading algorithm to multicarrier non-orthogonal multiple access (NOMA) systems to maximize the system total throughput while satisfying the users’ individual quality of service (QoS) constraints. Although bit loading is generally a non-deterministic polynomial-time (NP)-hard problem, even for orthogonal multiple access (OMA), the mutual interference between the users, and the dependence of power coefficients and modulation orders are additional challenges that add substantial complexity to the optimization problem. Therefore, in this paper, we propose an efficient bit loading algorithm for multicarrier NOMA systems and compare the complexity and throughput with a corresponding OMA system. The obtained results show that for the case of NOMA, bit loading provides an additional degree of freedom that allows non-uniform spectrum sharing among the users. In particular scenarios, the system may experience hybrid modes of operation, where the system switches between NOMA and OMA. The obtained numerical results show that NOMA can outperform OMA by 100% in terms of spectral efficiency, for a two-user scenario. The complexity of the loading process for NOMA is noticeably higher than OMA, which is due to the high complexity associated with the bit error rate (BER) computation in the case of NOMA. [ABSTRACT FROM AUTHOR]

This paper proposes on-driving experience sharing algorithms at junctions in infrastructure-assisted vehicles-to-everything networks. For the purpose, a millimeter-wave (mmWave) technology is used because it provides multi-Gbps data rates which is helpful for handling users’ short stay times at junctions and spatial reuse due to high beam directionality which is helpful for interference-avoidance among densely deployed vehicles at junctions. To realize on-driving experience sharing, the proposed algorithms focus on joint resource allocation and scheduling for 3GPP-compliant multiple unicast vehicle-to-vehicle (V2V) communications where the vehicles are group leaders (GLs) in 3GPP Mode 4(d). The resource allocation stands for the roadside unit (RSU) allocation to scheduled V2V GL links where RSU is essentially required for overcoming blockage by establishing two-hop relaying. Because vehicles stay for short times at junctions, this paper designs two algorithms without or with delay considerations. Without delay considerations, the joint optimization of RSU allocation and scheduling was originally formulated as mixed 0-1 non-convex optimization. However our proposed algorithm reformulates the problem into mixed 0-1 convex optimization, which is computationally easier to solve. With delay considerations, our proposed algorithm dynamically controls video contents frame rates for time-average on-driving video sharing quality maximization subject to delay constraints, inspired by Lyapunov optimization. Extensive simulation results demonstrate that our algorithms can significantly outperform in a variety of scenarios. Furthermore, we conduct the cost analysis for the proposed algorithms in terms of capital expenditure (CAPEX) and operating expenditure (OPEX). [ABSTRACT FROM AUTHOR]

The combination of non-orthogonal multiple access (NOMA) and intelligent reflecting surface (IRS) is an efficient solution to significantly enhance the energy efficiency of the wireless communication system. In this paper, a downlink multi-cluster NOMA network is considered, where each cluster is supported by one IRS. This paper aims to minimize the transmit power by jointly optimizing the beamforming, the power allocation and the phase shift of each IRS. The formulated problem is non-convex and challenging to be solved due to the coupled variables, i.e., the beamforming vector, the power allocation coefficient and the phase shift matrix. To address this non-convex problem, an alternating optimization based algorithm is proposed. Specifically, the primal problem is divided into two subproblems for beamforming optimization and phase shifting feasiblity, where the two subproblems are solved iteratively. Moreover, to guarantee the feasibility of the beamforming optimization problem, an iterative algorithm is proposed to search the feasible initial points. To reduce the complexity, a simplified algorithm based on partial exhaustive search for this system model is also proposed. Simulation results demonstrate that the proposed alternating algorithm can yield a better performance gain than the partial exhaustive search algorithm, NOMA with random IRS phase shift scheme and OMA-IRS scheme. [ABSTRACT FROM AUTHOR]

Grant-free non-orthogonal multiple access (NOMA) scheme is considered as a promising candidate for the enabling of massive connectivity and reduced signalling overhead for Internet of Things (IoT) applications in massive machine-type communication (mMTC) networks. Exploiting the inherent nature of sporadic transmissions in the grant-free NOMA systems, compressed sensing based multiuser detection (CS-MUD) has been deemed as a powerful solution to user activity detection (UAD) and data detection (DD). In this paper, block coordinate descend (BCD) method is employed in CS-MUD to reduce the computational complexity. We propose two modified BCD based algorithms, called enhanced BCD (EBCD) and complexity reduction enhanced BCD (CR-EBCD), respectively. To be specific, by incorporating a novel candidate set pruning mechanism into the original BCD framework, our proposed EBCD algorithm achieves remarkable CS-MUD performance improvement. In addition, the proposed CR-EBCD algorithm further ameliorates the proposed EBCD by eliminating the redundant matrix multiplications during the iteration process. As a consequence, compared with the proposed EBCD algorithm, our proposed CR-EBCD algorithm enjoys two orders of magnitude complexity saving without any CS-MUD performance degradation, rendering it a viable solution for future mMTC scenarios. Extensive simulation results demonstrate the bound-approaching performance as well as ultra-low computational complexity. [ABSTRACT FROM AUTHOR]

Vehicle and airborne navigation users are facing more and more complex signal interference and even spoofing. If vehicles and aircraft do not strengthen their anti-spoofing ability, their navigation performance is bound to be adversely affected. global navigation satellite system (GNSS) spoofing technology has gradually become a preferred interference method for spoofer because of its high concealment and great harm. For spoofer, user terminal increasingly adopts GNSS with inertial measurement unit (IMU): tightly-coupled GNSS/IMU, on this basis, user also configures a variety of anti-spoofing techniques to effectively deal with spoofing. Even if spoofer slowly changes user's positioning, if spoofing strategy is unreasonable, it will lead to the violation of parameter rationality of coupled filter output parameters and spoofing observation, which greatly increases the difficulty of spoofing. In view of the above problems, from the perspective of spoofer, in order to effectively counter the non cooperative target of assembling tightly-coupled GNSS/IMU by using GNSS spoofing, this paper establishes GNSS spoofing mathematical model, and proposes a slowly varying spoofing algorithm to avoid tightly-coupled GNSS/IMU with multiple anti-spoofing techniques based on the analysis of the influence mechanism of spoofing on the positioning of tightly-coupled GNSS/IMU, the algorithm proposes a measurement deviation determination method to avoid a variety of anti-spoofing techniques, which can gradually pull the positioning results of coupled system, and successfully avoid anti-spoofing techniques detection of least squares residual receiver autonomous integrity monitoring (RAIM) and parameter rationality check. The experimental results show that the algorithm can gradually change positioning of tightly-coupled GNSS/IMU within 30 s, and the north, east and down displacements basically achieve the spoofing effect, the errors with the expected offset are −0.5 m, 1.9 m and 12.7 m respectively. At the same time, the detection of the above anti-spoofing techniques is avoided. The mean value of test statistics for tightly-coupled system is reduced by 75.4% and does not exceed the alarm threshold, so as to achieve the purpose of spoofing, the effectiveness and high concealment of the spoofing algorithm are proved. [ABSTRACT FROM AUTHOR]

For vehicle-to-network communications, handover (HO) management enables vehicles to maintain the connection with the network while transiting through coverage areas of different base stations (BSs). However, the high mobility of vehicles means shorter connection periods with each BS that leads to frequent HOs, hence raises the necessity for optimal HO decision making for high quality infotainment services. Machine learning is capable of capturing underlying pattern via data driven methods to find optimal solutions to complex problems, and much learning-based HO optimization research has been conducted focusing on specific network setups. However, attention still needs to be paid to the actual deployment aspect and standardized datasets or simulation environments for evaluation. This paper proposes a deep reinforcement learning-based HO algorithm using the input parameters that are configurable in the existing measurement report of cellular networks. The performance of the proposed algorithm is evaluated using the well-known network simulator ns-3 with its official LTE module. A realistic network setup in the city center of Glasgow (U.K.) is configured with vehicle trajectories generated by the routes mobility model using Google Maps Directions API. Evaluation results reveal that the proposed algorithm significantly outperforms the A3 RSRP baseline with an average of 25.72% packet loss reduction per HO, suggesting significant improvement in quality of service of phone call and video streaming, etc. The proposed algorithm also has a small implementation cost compared to some state-of-the-art and should be deployed by a software update to a local BS controller. [ABSTRACT FROM AUTHOR]

This paper considers the hybrid precoder design in millimeter wave (mmWave) multi-input multi-output (MIMO) systems with low-resolution analog phase shifters. Aiming at reducing the complexities of the near-optimal algorithms, we propose a low-complexity multi-user hybrid precoding scheme based on tree-coding-aided adaptive-cross-entroy (TC-ACE) algorithm. By defining some discrete variables for the analog precoders and combiners, the problem of hybrid precoding is transformed into a cross-entroy (CE) optimization problem, which can be solved by iteratively updating the probability distributions of the predefined discrete variables. In order to derive the closed-form expression of the probability distributions, tree-coding is used to encode each entry of the analog precoders and combiners with a binary number. Through iterations, optimal analog precoders and combiners will be obtained when its probabilities are sufficiently high. Simulation results show that when the number of users exceeds a certain value, the proposed scheme outperforms the alternating minimization algorithm and coordinate descent method in terms of both the sum-rate and complexity. [ABSTRACT FROM AUTHOR]

Cooperative Vehicle-Infrastructure System (CVIS) can provide innovative services for traffic management and enable trips to be safer, more coordinated, and smarter. In the CVIS, the vehicles upload crowd sensing data to the Vehicular Edge Computing (VEC) server for quick data fusion and informed decision-making. However, with the ever-increasing number of vehicles, the VEC server cannot undertake massive computation-intensive tasks due to the limited edge computing capabilities. In this paper, we propose a reverse offloading framework that can fully utilize the vehicular computation resource to relieve the burden of the VEC server and further reduce the system latency. Under the proposed offloading framework, the binary reverse offloading (BRO) and partial reverse offloading (PRO) strategies are designed for two types of tasks, i.e., non-partitioned tasks and partitioned tasks. We formulate the system latency minimization problem by optimizing reverse offloading decisions, and the communication and computation resources allocation. Due to the non-convex and existing variables coupling, the original problem is transformed into the equivalent weighted-sum optimization problem. Based on the alternative optimization, we decouple the weighted-sum optimization problems into the two subproblems, and the closed-form expressions of transmission power and computation frequency of vehicles and RSU are derived. Low complexity greedy based efficient searching (GES) algorithm and joint alternative optimization based bi-section searching (JAOBSS) algorithm are proposed for BRO and PRO strategies, respectively. The algorithm complexity and performance bounds are analyzed. Simulation results show that the proposed GES algorithm can achieve optimal performance with low complexity. Besides, the proposed GES and JAOBSS algorithms can significantly improve the performance compared with other baseline schemes by 6.14% and 13.46% at least. [ABSTRACT FROM AUTHOR]

Range-based positioning using wireless signal has gained remarkable attention in past decades. Accurately extracting the distance information, i.e., estimating parameters of individual multipath, is of interest. It has been shown that diffuse multipath component (DMC) in wireless propagation channel has significant influence on channel estimation and, thus, the ranging performance. In addition to specular component (SC), DMC should be considered in order to improve the estimated accuracy of channel paths’ parameters and, thus, the ranging performance. In this paper, we extend the quasi-maximum likelihood space-alternating generalized expectation-maximization (SAGE) algorithm by incorporating an autoregressive moving average (ARMA) filter to estimate the channel parameters under the presence of DMC. The parameters of both DMC and SC are estimated in an iterative approach, where the DMC is assumed as colored noise and the ARMA-filter is used to estimate the contributions from DMC. The validation of the algorithm based on measured data shows that both SC and DMC can be accurately estimated by the proposed approach. A comparison with standard SAGE and AR-SAGE is conducted, where the results reveal that the proposed method outperforms other two approaches in terms of ranging accuracy. [ABSTRACT FROM AUTHOR]

In this paper, an intelligent reflecting surface (IRS) is deployed to assist the terahertz (THz) communications. The sum-rate of user equipments (UEs) is maximized while guaranteeing the rate requirement of each UE. A block coordinate searching (BCS) algorithm is proposed to jointly optimize the IRS’s coordinates, phase shifts, THz sub-bands allocation and power control. Specifically, the relaxation with penalties based (RPB) algorithm is developed to obtain feasible coordinates of the IRS and guarantee the monotonicity of objective value. In addition, the IRS phase shifts are formulated as closed-form expressions with introduced pricing factors. Simulation results show that the proposed scheme can significantly enhance system performance. [ABSTRACT FROM AUTHOR]

In this paper, we consider a computation offloading problem in a three-tier network consisting of multiple mobile users (MUs), multiple edge clouds, and a central cloud. On this basis, we formulate a system Energy Time Cost ($ETC$) minimization problem by jointly optimizing the resource allocation, mobile-edge matching decision, and offloading decision. Due to the difficulty of directly solving the formulated problem, we decompose it and propose two offloading algorithms, namely Gale-Shapley based Minimum/Sequential Offloading Algorithm (GS-MOA/GS-SOA), to optimize offloading decisions by minimizing the system $ETC$ , in which the mobile-edge matching strategies based on the proposed Gale-Shapley based Mobile-Edge mAtching aLgorithm (GS-MEAL) and resource allocations are optimized iteratively. The simulations show the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we propose an adaptive vehicle clustering algorithm based on fuzzy C-means algorithm, which aims at minimizing power consumption of the vehicles. Specifically, the proposed algorithm firstly dynamically allocates the computing resources of each virtual machine in the vehicle, according to the popularity of different virtualized network functions. The optimal clustering number to minimize the total energy consumption of vehicles is determined using the fuzzy C-means algorithm and the clustering head is selected based on vehicles moving direction, weighted mobility, and entropy. Simulation results are provided to confirm that the proposed algorithm can decrease the power consumption of vehicles while satisfying the vehicle delay requirement. [ABSTRACT FROM AUTHOR]

Dq impedance measurement is of great importance as a part of the impedance-based analysis. At present, impedance of objects in single-phase vehicle-grid system are mainly obtained by injecting the voltage or current disturbance of one single frequency into the system circularly. However, as the number of measurement frequency points increases, there will produce much time-consuming of measurement. In this paper, a quick dq impedance measurement algorithm for single-phase vehicle-grid system based on multi-frequency sweep is proposed. First, pseudo-random binary sequences (PRBS) and ternary sequences are modified as the driving signals rather than directly injecting into the control link. Then three types of disturbance with specific frequency characteristics are introduced into the system and their parameters setting principle are given for the first time. According to the different characteristics of measurement objects, the proposed algorithms are also different to ensure the maximum specificity and sensitivity. Finally, for different objects in vehicle-grid system like traction network, single-phase converter and dual-interleaved converter, simulation and experimental results based on the hardware in the loop real-time simulation platform both show the correctness of the proposed algorithm, and the possible causes of errors are also analyzed in detail. Moreover, the proposed algorithm makes it possible to quickly measure the dq impedance of the single-phase vehicle-grid system, and the correctness of the theoretical and measured value can be judged and used for the stability analysis of electrical systems. [ABSTRACT FROM AUTHOR]

This paper aims to explore the performance potential of a novel dual-mode power-split hybrid powertrain. First, the steady-state power split characteristics for the proposed hybrid powertrain in different modes are analyzed. The mode switching strategy is developed to maximize powertrain efficiency, which is verified by using dynamic programming based on direct transmit points (DTPs). Moreover, a novel multi-objective evolutionary algorithm based on the decomposition (MOEA/D) method used in a nested way with dynamic programming is proposed to solve the multi-objective optimization of the PS-HEVs for the first time, and the computational efficiency and superiority of the proposed algorithm is compared with the commonly used NSGA-II algorithm. The results show that the MOEA/D based multi-objective optimization framework has similar performance in the search for the Pareto frontier but significantly higher computational efficiency than that of the NSGA-II algorithm. The obtained Pareto frontier provides optimal design candidates for hybrid powertrain systems. [ABSTRACT FROM AUTHOR]

This paper investigates the sub-channels and power allocation issue in the multi-carrier NOMA communication system. To maximize the sum rate of the system, we design a fast dynamic resource allocation (FDRA) algorithm. The algorithm can quickly identify the interference nodes with poor channel conditions, and reduces the search complexity of the algorithm. By jointly optimizing sub-carrier and power resource allocation, the proposed scheme can take full advantage of the channel capacity, and maximize the system performance while ensuring the quality of service (QoS) of each user. Simulation results show that when compared with the joint resource allocation (JRA) algorithm and the genetic algorithm (GA), the FDRA algorithm can achieve the best performance on the complexity and the sum rate of the system. Thus, the proposed algorithm can provide a fast and efficient resource allocation scheme for the downlink multi-carrier NOMA systems. [ABSTRACT FROM AUTHOR]

In this paper, we propose three new compressive sensing-based algorithms for channel estimation in millimeter wave hybrid MIMO systems over doubly (time and frequency) selective channels. Utilizing the basis expansion model (BEM) for effectively representing doubly selective channels, we first propose a BEM-based block orthogonal matching pursuit (BBOMP) algorithm, which can work with any training sequence structure. Next, we present the second algorithm to reduce the complexity of the BBOMP method by employing a special training sequence which results in a computationally efficient block sparse sensing matrix. Finally, in order to further decrease the computational complexity, we propose the third algorithm, where the channel estimation is split into two separate steps of tap detection and gain estimation. The proposed algorithms exploit the entire available training sequence to estimate all channel parameters, and can capture channel variations across the entire training frames without requiring a feedback channel. The Cramer-Rao lower bound and the computational complexity of the proposed algorithms are also addressed. Intensive computer simulations are conducted to evaluate the accuracy of the proposed approaches, showing that they can significantly improve the mean squared error performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to accurately and efficiently identifying a large number of wireless devices blindly installed to known three-dimensional installation/fitting points, based on received signal strengths (RSSs) between the devices. The approach is non-trivial because of the factorial, mapping nature of the considered problem, the multiplicative ranging errors of the RSS measurements (with standard deviation of 5–7 dB), and the requirement of high mapping accuracy in many internet-of-things (IoT) applications, e.g., industrial IoT and aircraft. The consideration of a structured environment where the set of candidate node positions is known beforehand shifts the problem of interest from a pure position estimation problem to a position assignment problem. The key idea of the proposed approach is that we interpret the position mapping problem with a probabilistic graphical model, where the factorial nature of mapping (more specifically, the mutual exclusiveness of devices at every installation point) is fully captured. A max-product belief propagation is designed against the probabilistic graph, to estimate the max-marginal position distribution of each device. The Kuhn-Munkres algorithm is applied to preserve the mutual exclusiveness of devices throughout the belief propagation and to decide device locations based on the estimated position distributions. Large-scale simulations and field tests are carried out, showing that the new approach achieves close-to-100% accuracy in simulations with hundreds of blindfolded devices under RSS measurement errors with standard deviation of 5–7 dB. Our approach also achieves 100% accuracy in all field trials with 76 devices inside the cabin of a Fokker 100 airplane, dramatically outperforming baseline techniques. [ABSTRACT FROM AUTHOR]

Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]

Power control is becoming increasingly essential for the fifth-generation (5G) and beyond systems. An example use-case, among others, is the unmanned-aerial-vehicle (UAV) communications where the nearly line-of-sight (LoS) radio channels may result in very low signal-to-interference-plus-noise ratios (SINRs). The authors in (Chiang et al., 2007) proposed to efficiently and reliably solve this kind of non-convex problem via a series of geometrical programmings (GPs) using condensation approximation. However, it is only applicable for a small-scale network with several communication pairs and practically infeasible with more (e.g., tens of) nodes to be jointly optimized. We therefore in this paper aim to provide new insights into this problem. By properly introducing auxiliary variables, the problem is transformed to an equivalent form which is simpler and more intuitive for condensation. A novel condensation method with linear complexity is also proposed based on the form. The enhancements make the GP-based power control feasible for both small- and especially large-scale networks that are common in 5G and beyond. The algorithm is verified via simulations. A preliminary case study of uplink UAV communications also shows the potential of the algorithm. [ABSTRACT FROM AUTHOR]

This paper considers optimal joint time, frequency, and power allocation for energy-efficient device-to-device (D2D) communications in an overlay cellular network, where multiple D2D transmitters communicate with their corresponding D2D receivers while utilizing the energy harvested from a cellular base station (BS). Due to channel estimation error and feedback delays, the channel state information (CSI) available at the transmitters is usually imperfect, which can significantly deteriorate the energy efficiency (EE) of the considered system. To mitigate the impact of imperfect CSI, we formulate a non-convex robust optimization problem for the maximization of the EE (in bits/Joule) of the system while ensuring quality of service (QoS) requirements on the minimum data rata and the minimum amount of harvested energy for cellular and D2D users, respectively. We reveal that the optimal energy-efficient D2D transmission should exhaust all the harvested energy of each D2D transmitter. Exploiting this fact, we propose an efficient iterative algorithm for obtaining the optimal solution. To strike a balance between performance and computational complexity, we further propose a low-complexity suboptimal algorithm. Simulation results show that compared with several baseline schemes, both the proposed optimal and suboptimal algorithms can significantly improve the EE of wireless-powered D2D communications under imperfect CSI. Moreover, the proposed suboptimal algorithm is close-to-optimal when the number of cellular users are small or the channel estimation error is large. [ABSTRACT FROM AUTHOR]

Two-Way Ranging (TWR) is a widely used method for distance estimation in asynchronous wireless networks, but the deviation between the clocks can lead to errors in distance estimation. The ultra-wideband (UWB) technology provides the best accuracy in distance estimation, but total emission time is drastically limited by harmonized standards. Localization accuracy, latency and network scalability are key performance metrics in wireless location characterization. This article advances a new sequencing of the localization process, called Double-Beacon Two-Way Ranging (DB-TWR) algorithm, and presents the related time-of-flight (ToF) estimation formula, which is able to compensate for clock error and to reduce the localization period. The Fine Time Measurement (FTM) protocol, specified by the Wireless LAN (WLAN) standard, uses the TWR method and as a result the clock deviation leads to systematic errors in ToF estimation. The paper proposes two additional timestamp s captures and a new ToF computation formula which compensates for clock deviation. The article provides a theoretical analysis and extensive simulations of errors propagation in the ranging process, both as a mean and as an uncertainty, and proves that the designed algorithms cancel the clock offsets entirely. [ABSTRACT FROM AUTHOR]

In this paper, a novel beam alignment algorithm based on the sparse graph coding theory is proposed for millimeter wave (mmWave) time-varying channels. Firstly, a pilot design method is introduced to transform the mmWave time-varying beam alignment into a sparse-graph design and detection problem. Inspired by Low-Density-Parity-Check (LDPC) codes and fountain codes, a multi-stage sparse coding method is proposed for the design of the measurement matrix and the theoretical bound of the probability of success is derived to guide the design of the sparse-graph. A beam alignment algorithm is subsequently proposed to detect the beam index and estimate the carrier frequency offset (CFO). Then, the Carmeŕ-Rao Lower Bound (CRLB) is derived. Simulation results demonstrate that the proposed beam alignment algorithm achieves significant performance improvements over the conventional counterparts in both the noiseless and noise cases. [ABSTRACT FROM AUTHOR]

During the running of electric locomotives, a large amount of operating data will be stored through the Analog-Digital Converter (ADC) and the recording oscillograph of the on-board Traction Control Unit (TCU). Analysis based on mass data to detect slipping is of great significance for saving energy, improving the performance and safety of the traction control system of electric locomotives. Therefore, after analyzing and summarizing the advantages of Empirical Wavelet Transform (EWT) and Fuzzy Entropy (FE) algorithm in data processing and the classification theory of Support Vector Machine (SVM), this paper proposed a SVM slipping detection method based on EWT and FE algorithm. Firstly, feature extraction is carried out on the locomotive wheelset velocity data collected by the on-board velocity sensor, that is, the feature vector of data is extracted by calculating fuzzy entropy value after EWT, and the velocity data is converted into feature matrix for slipping-detection of SVM. Then considering the defects of traditional optimization algorithms such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) in the parameter optimization of SVM, Genetic Particle Swarm Optimization Algorithm (GAPSO) is proposed to optimize the parameters of SVM classification model, and the slipping detection model of SVM is established through training samples, which realizes high-precision slipping detection. Finally, combined with a large number of locomotive data, the comparative analysis test is carried out, the results show that the feature extraction method based on EWT and FE algorithm has excellent ability of mode decomposition and feature extraction, GAPSO has efficient optimization ability, and the proposed slipping detection method can accurately detect slipping. [ABSTRACT FROM AUTHOR]

This paper investigates a dynamic 3D trajectory design of multiple cache-enabled unmanned aerial vehicles (UAVs) in a wireless device-to-device (D2D) caching network with the goal of maximizing the long-term network throughput. By storing popular content at the nearby mobile user devices, D2D caching is an efficient method to improve network throughput and alleviate backhaul burden. With the attractive features of high mobility and flexible deployment, UAVs have recently attracted significant attention as cache-enabled flying base stations. The use of cache-enabled UAVs opens up the possibility of tracking the mobility pattern of the corresponding users and serving them under limited cache storage capacity. However, it is challenging to determine the optimal UAV trajectory due to the dynamic environment with frequently changing network topology and the coexistence of aerial and terrestrial caching nodes. In response, we propose a novel multi-agent reinforcement learning based framework to determine the optimal 3D trajectory of each UAV in a distributed manner without a central coordinator. In the proposed method, multiple UAVs can cooperatively make flight decisions by sharing the gained experiences within a certain proximity to each other. Simulation results reveal that our algorithm outperforms the traditional single- and multi-agent Q-learning algorithms. This work confirms the feasibility and effectiveness of cache-enabled UAVs which serve as an important complement to terrestrial D2D caching nodes. [ABSTRACT FROM AUTHOR]

Drones have a wide range of applications in urban environments as they can both enhance people's daily activities and commercial activities through various operations and deployments. With the increasing number of drones, flight safety and efficiency become the main concern, and effective drone operations can make a difference. Accordingly, 4D path planning for drone operations is the focus of this paper, and the swarm-based method is proposed to solve this complicated optimization problem. Under the framework of ‘AirMatrix’, the problem is solved in two levels, i.e., 3D path planning for a single drone and conflict resolution among drones. In the multi-path planning level, multiple alternative flight paths for each drone are generated to increase the acceptance rate of a flight request. The constraints on a single flight path and two different flight paths are considered. The goal is to obtain several different short flight paths as alternatives. A clustering improved ant colony optimization CIACO) algorithm is employed to solve the multi-path planning problem. The crowding mechanism is used in clustering, and some improvements are made to strengthen the global and local search ability in the early and later phases of iterations. In the task scheduling level, the conflicts between two drones are defined in two circumstances. One is for the time interval of passing the same path point, another one is for the right-angle collision between two drones. A three-layer fitness function is proposed to maximize the number of permitted flights according to the safety requirement, in which the airspace utilization and the operators’ requests are both considered. A ‘cross-off’ strategy is developed to calculate the fitness value, and a ‘distributed-centralized’ strategy is applied considering the task priorities of drones. A genetic algorithm GA)-based task scheduling algorithm is also developed according to the characteristic of the established model. Simulation results demonstrate that 4D flight path of each drone can be generated by the proposed swarmed-based algorithms, and safe and efficient drone operations in a specific airspace can be ensured. [ABSTRACT FROM AUTHOR]

This paper studies how to apply game theory to realize a well-function device-to-device enabled vehicular (D2D-V) communication system, where the uplink channel allocated to the cellular user (CU) is reused by multiple D2D-V users. Considering a non-cooperative setting where the CU and D2D-V users are selfish and profit-driven, a novel Stackelberg game framework is proposed to model the single-leader-multiple-follower hierarchical competition, where the CU and D2D-V users act as the leader and the followers, respectively. For the current D2D-V networks, the interference in the dense vehicle scene often leads to extremely poor communication quality. Moreover, a vehicle's mobility leads to an uncertain channel state and further affects the stability of communication. To achieve effective communication, robust Stackelberg game-based resource allocation is developed, and a price-penalty mechanism is further proposed. Unlike previous Stackelberg games, the robust game is highlighted by handling the channel uncertainty which is embedded in the interference probability constraints. Besides, a game equilibrium (GE) is considered to be the solution and its existence and uniqueness are investigated. Also, a distributed robust power control and nonuniform price bargaining algorithm is proposed to approach the GE. Numerical simulations are performed to evaluate the algorithm performances, and the results indicate that the proposed algorithm is effective in high mobility vehicular networks under uncertain channel environments. [ABSTRACT FROM AUTHOR]

This paper investigates a wireless powered mobile edge computing (MEC) network where a hybrid access point (H-AP) serves energy-constrained devices. For such a wireless powered MEC network, the H-AP first transmits wireless information and energy simultaneously in the downlink. Then, by utilizing the harvested energy, the device processes both its local data and the received data from the H-AP. In this system, we minimize the latency by jointly optimizing the power splitting ratio of rectifiers, the data offloading power, the local computing frequency, and the data offloading ratio at the device. By applying a polyblock outer approximation procedure, we propose an algorithm which guarantees the optimal solution. Simulation results verify the efficiency of the proposed algorithm compared to conventional schemes. [ABSTRACT FROM AUTHOR]

Carrier Aggregation is one of the vital approaches to achieve several orders of magnitude increase in peak data rates. While carrier aggregation benefits have been extensively studied in cellular networks, its application to satellite systems has not been thoroughly explored yet. Carrier aggregation can offer an enhanced and more consistent quality of service for users throughout the satellite coverage via combining multiple carriers, utilizing the unused capacity at other carriers, and enabling effective interference management. Furthermore, carrier aggregation can be a prominent solution to address the issue of the spatially heterogeneous satellite traffic demand. This paper investigates introducing carrier aggregation to satellite systems from a link layer perspective. Deployment of carrier aggregation in satellite systems with the combination of multiple carriers that have different characteristics requires effective scheduling schemes for reliable communications. To this end, a novel load balancing scheduling algorithm has been proposed to distribute data packets across the aggregated carriers based on channel capacities and to utilize spectrum efficiently. Moreover, in order to ensure that the received data packets are delivered without perturbing the original transmission order, a perceptive scheduling algorithm has been developed that takes into consideration channel properties along with the instantaneous available resources at the aggregated carriers. The proposed modifications have been carefully designed to make carrier aggregation transparent above the medium access control (MAC) layer. Additionally, the complexity analysis of the proposed algorithms has been conducted in terms of the computational loads. Simulation results are provided to validate our analysis, demonstrate the design tradeoffs, and to highlight the potentials of carrier aggregation applied to satellite communication systems. [ABSTRACT FROM AUTHOR]

To meet the execution requirements of delay-sensitive services in vehicular edge computing (VEC) networks, vehicular services need to be offloaded to edge computing nodes. For complex, large-scale services, the services need to be migrated if the services are not completed before the vehicles leave the coverage of edge computing nodes. Trust and resource matching between areas thus become major problems. This paper studies the decision model of vehicular service offloading and migration. First, software-defined network (SDN) technology is introduced into the traditional network architecture, and a two-layer distributed SDN-controlled VEC network architecture is designed, which is divided into a domain control layer and an area control layer. In this framework, we use the consortium blockchain as a carrier to share network topology information between SDN controllers to prevent information leakage. We then established a service offloading and migration optimization problem model to minimize service execution delay, reduce energy consumption and maximize the throughput of the blockchain system. We describe the problem model as a Markov Decision Process (MDP), introduce a deep reinforcement learning (DRL) algorithm named asynchronous advantage actor-critic (A3C) and design a dynamic service offloading and migration algorithm (DSOMA) based on A3C to solve the problem. Simulation results show that DSOMA can increase the throughput of the blockchain system, and DSOMA is superior to the deep Q-learning (DQN) algorithm and greedy offloading algorithm in reducing service execution delay and system energy consumption. [ABSTRACT FROM AUTHOR]

Articulation angle sensing is an essential component of manoeuvrability and stability control systems for articulated heavy goods vehicles, particularly long combination vehicles. Existing solutions to this sensing task are limited by reliance on trailer modifications or information or by measurement accuracy, or both, restricting commercial adoption. In this paper we present a purely tractor-based sensor concept comprising a rear-facing camera and the parallel tracking and mapping (PTAM) image processing algorithm. The system requires no prior knowledge of or modifications to the trailer, is compatible with planar and non-planar trailer shapes, and with multiply-articulated vehicle combinations. The system is validated in full-scale vehicle tests on both a tractor semi-trailer combination and a truck and full-trailer combination, demonstrating robust performance in a number of conditions, including trailers with non-planar geometry and with minimal visual features. Average RMS measurement errors of 1.19, 1.03 and 1.53 degrees were demonstrated for the semi-trailer and full-trailer (drawbar and semi-trailer) respectively. This compares favourably with the state-of-the-art in the published literature. A number of improvements are proposed for future development based on the observations in this research. [ABSTRACT FROM AUTHOR]

This paper proposes a flexible pilot assignment method to jointly optimize the uplink and downlink data transmission in multi-cell Massive multiple input multiple output (MIMO) systems with correlated Rayleigh fading channels. By utilizing a closed-form expression of the ergodic spectral efficiency (SE) achieved with maximum ratio processing, we formulate an optimization problem for maximizing the minimum weighted sum of the uplink and downlink SEs subject to the transmit powers and pilot assignment sets. This combinatiorial optimization problem is solved by two sequential algorithms: a heuristic pilot assignment is first proposed to obtain a good pilot reuse set and the data power control is then implemented. Numerical results manifest that the proposed algorithm converges fast to a better minimum sum SE per user than the algorithms in previous works. [ABSTRACT FROM AUTHOR]

It has been well-recognized that clustered Interference alignment (IA) can provide remarkable interference suppression performance for the existing small cell networks (SCNs). There is also a tendency that full-duplex (FD) radios would replace the half-duplex radios at future small base stations (SBSs). In this context, the intra-cell and inter-cell interference in SCNs would become much more serious, where the performance of clustered IA has not been evaluated yet. In this paper, we explore the maximum achievable sum-rate of the FD-based SCNs when clustered IA combined with power control strategy is applied. To achieve this, a mixed-integer optimization problem is formulated, which is furtherly decoupled into two subproblems for ease of handling. Then we propose the minimized rate loss (MRL) algorithm to address the clustering subproblem and a convex approximation method to address the power control subproblem. The two subproblems are performed alternatively till the sum-rate gains convergence. Preliminary simulations clearly demonstrate that the achievable sum-rate is limited by the number of antennas at the users. [ABSTRACT FROM AUTHOR]

The measurement of received signal strength (RSS) and channel state information (CSI) has been widely used in the research of device-free localization (DFL). However, DFL systems based on these systems usually require labour-intensive training to understand the impact of the target on the surrounding wireless signals to build the target location-related model or image. In addition, the fact that the RSS is susceptible to multipath interference and is not directly accessible to CSI directly limits its actual deployment. In this paper, we explore the feasibility of DFL based on time-of-flight measurements of ultra-wideband signals, and propose a fusion method for simultaneous localization of multiple targets based on the evaluation results. Specifically, we mesh the feasible region of the target and utilize the geometric filtering method to re-evaluate the filtered wireless links in combination with the real-time adaptive relaxation target model. Consequently, we introduce the clustering method and combine the category matching strategy to ensure that the algorithm has robust real-time multi-target perception ability. Extensive experiments conducted in the lobby, laboratory and office scenarios demonstrate that the proposed method plays an active role in more than 82% and can control the mean error within 0.6 m. [ABSTRACT FROM AUTHOR]

In this paper, the backward-compatible coding schemes are explored to achieve the near-capacity performances in dynamic LDPC-coded Gaussian multiple access channels (GMAC). Specifically, some user-load-compatible (ULC) masked edges in a raptor-like protograph are masked with the variation of user load u. To distinguish the edges in a protograph, a multi-user protograph-based extrinsic information transfer (MU-PEXIT) chart is developed. Based on this chart, an iterative edge selection algorithm combined with a theoretical simplification is proposed to facilitate the selection of independent masked edge sets (MESs) for varying u. To further decrease the complexity of the independent masking scheme, a nested version is presented, where the MESs for varying u are nested and derived from the same mother MES. Meanwhile, nested selection algorithms are provided to select the nested MESs. Extensive simulation results demonstrate that the masked 5G-NR LDPC codes can maintain near-capacity performances regardless of the variation of u. Besides, these ULC masked codes achieve comparable performances with the state-of-the-art LDPC codes which are specially re-designed in a static GMAC. [ABSTRACT FROM AUTHOR]

The orbital angular momentum (OAM)-based communication systems may face severe transmission problems when the transmit and receive uniform circular array pairs are blocked. In this paper, a promising technique named intelligent reflecting surface (IRS) is proposed to help alleviate blockages and provide alternative line-of-sight links. To maximize the achievable rate of the IRS-assisted OAM communication systems, we optimize its transmit power allocation along with the IRS's reflecting phase shifts, and propose an alternative optimization-based algorithm to solve the resulting optimization problem with coupled variables and non-convex structure. Specifically, the proposed algorithm obtains a closed-form solution to the transmit power allocation by applying the majorization-minimization and ℓ1-ball projection approaches, and obtain the locally optimal solution to the IRS's reflecting phase shifts by applying the weighted minimum mean square error-based fixed point iteration approach. Simulation results demonstrate the superiority of our proposed algorithm over existing baseline algorithms and also show its robust stability to the oblique angle errors. [ABSTRACT FROM AUTHOR]

This paper investigates unmanned aerial vehicle (UAV) data collection systems with different multiple access schemes, where a rotary-wing UAV is dispatched to collect data from multiple ground nodes (GNs). Our goal is to maximize the minimum UAV data collection throughput from GNs for both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) transmission, subject to the energy budgets at both the UAV and GNs, namely double energy limitations. 1) For OMA, we propose an efficient algorithm by invoking alternating optimization (AO) method, where each subproblem is alternately solved by applying successive convex approximation (SCA) technique. 2) For NOMA, we first handle subproblems with fixed decoding order using SCA technique. Then, we develop a penalty-based algorithm to solve the decoding order design subproblem. Numerical results show that: i) The proposed algorithms are capable of improving the max-min throughput performance compared with other benchmark schemes; and ii) NOMA yields a higher performance gain than OMA when GNs have sufficient energy. [ABSTRACT FROM AUTHOR]

This paper presents a Gaussian tracking algorithm with direction-of-arrival (DOA) measurements modelled via the Kent distribution. The key aspect of the algorithm is that the Kent distribution directly models the specific characteristics of DOA measurements in the 3-D space, and can account for different uncertainties in azimuth and elevation, which the von Mises-Fisher distribution cannot. At each update step, the algorithm performs iterated statistical linear regressions. We provide two implementations of the algorithms, one based on sigma-points and the other on analytical linearisation. The effectiveness of the approach is evaluated via numerical simulations. [ABSTRACT FROM AUTHOR]

Dynamic battery modeling uncertainties, even if low, may lead to significant performance degradation or even divergence of the state-of-charge estimation algorithm. This paper investigates the integration of the extended-Kalman-filter with the smooth-variable-structure-filter algorithms for state-of-charge estimation of lithium-ion batteries. The robustness of the presented approach to modeling uncertainty is assessed for batteries operating in highly dynamic environments. The presented approach combines the benefit of the smooth- variable-structure-filter in its robustness to model uncertainty with the benefit of the extended-Kalman-filter in its near-optimality for a given dynamics and measurement noise sequences. The algorithm is rigorously tested using various datasets including standardrized and artificial drive cycles with added dynamics. The drive cycle power profile is calculated for an electric Ford F150 truck and scaled for the 18650PF cell used in the tests. Experimental validation is performed by investigating four different scenarios in which knowledge of the initial conditions as well as accuracy of the battery model were varied. The results demonstrate a substantially enhanced estimation accuracy achieved by the adopted approach through its optimality to measurement and model noise as well as its robustness to model uncertainty. The adopted approach results in a reduction in the complexity of the state-of-charge control algorithm and therefore enhances the battery management system. [ABSTRACT FROM AUTHOR]

Massive multiple-input multiple-output (MIMO) with lens antenna array, referred to as beamspace MIMO, is attractive for millimeter wave (mmWave) communications, since it can realize the adequate beamforming gain with a small number of radio frequency (RF) chains. This paper addresses wideband channel estimation for mmWave beamspace MIMO. Specifically, a two-stage channel estimation scheme is proposed. In the first stage, we utilize multi-task sparse Bayesian learning (MT-SBL) to coarsely estimate the beamspace channel vectors, each corresponding to one OFDM subcarrier. In the second stage, we re-formulate the channel estimation problem by artfully exploiting the characteristics of beamspace channels. Then we develop an expectation maximization (EM) based algorithm to estimate the parameters involved in the formulation, thereby refining the channel estimates. Compared with the state-of-the-art counterparts, the proposed scheme can achieve much better performance while requiring a lower training overhead. [ABSTRACT FROM AUTHOR]

The present paper is dedicated to the investigation of a predictive Equivalent Consumption Minimization Strategy. The objective is to determine the torque split between the internal combustion engine and the electric machine of a hybrid vehicle. The energy management is formulated as a receding optimization problem. To avoid a complex prediction of the vehicle speed and acceleration over time, the slow dynamic of their distribution is exploited. A rational tuning of the algorithm parameters is proposed as well as some improved implementations. The number of individual operations (additions, multiplications, interpolations, etc) required per seconds is discussed. Finally, the energy management algorithm energy consumption are assessed over different driving cycles, including one with a \boldsymbol 15406  ${km}$ length obtained using GPS measurements. A comparison with an adaptive Equivalent Consumption Minimization Strategy is provided. The predictive Equivalent Consumption Minimization Strategy allows controlling the state of charge close to a (possibly time varying) set point while providing low fuel consumption. [ABSTRACT FROM AUTHOR]

Radio resource slicing is critical to customize service provisioning in fifth-generation (5G) uplink radio access networks (RANs). Using drone-small-cells (DSCs) as aerial support for terrestrial base stations can enhance the flexibility for resource provisioning in response to traffic distribution variations. In this paper, we study a multi-DSC-assisted radio resource slicing problem for 5G uplink RANs, with the objective of minimizing the total uplink resource consumption under differentiated quality-of-service (QoS) constraints for both human-type and machine-type communication services. We begin with an interference-aware graph model to formulate the joint DSC three-dimension (3D) placement and device-DSC association problem for uplink radio resource slicing and prove that the proposed problem is NP-hard. A complexity-adjustable problem approximation is presented via screening candidate DSC deployment positions, which incorporates flight height adaptation to balance the uplink communication coverage and resource utilization. A lightweight approximation using a fixed DSC flight altitude is also provided with reduced complexity. For mathematical traceability, the DSC placement and device-DSC associations in each approximation are transformed as a special weight clique problem. An upgraded clique algorithm is then developed to determine how to deploy DSCs for a given number of DSCs. Simulation results demonstrate the proposed scheme's effectiveness in terms of resource utilization, network coverage, and drone dispatching cost. [ABSTRACT FROM AUTHOR]

This paper studies a novel design of user pairing and resource allocation in a simultaneous wireless information and power transfer (SWIPT)-enabled cooperative non-orthogonal multiple access (NOMA) system with coexisting power-splitting (PS) and time-switching (TS) users. In this system, near NOMA users (NUs) that are close to a source can assist the communications between the source and far NOMA users (FUs) using the energy harvested by either PS or TS strategy. The design aims to maximize the sum-rate of the system by optimizing user pairing and power allocation between NUs and FUs as well as performing PS and TS control at NUs, while guaranteeing the target data rates and the minimum harvested energy requirements of users. Since the joint design is formulated as a non-convex mixed-integer non-linear programming (MINLP) problem that is challenging to tackle, we propose a two-step user pairing and resource allocation algorithm. Specifically, we decouple the original problem into an inner resource allocation problem and an outer user pairing problem. For the inner problem, we propose successive convex approximation (SCA) and block coordinate descent (BCD)-based algorithms to perform power allocation as well as PS and TS control iteratively, with the algorithms’ convergence being theoretically proved. By exploiting the characteristics of the outer problem of user pairing, this problem is well tackled by the Hungarian algorithm. Simulation results demonstrate the proposed joint design yields better performance gains than the existing schemes. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) or drone, is an evolving technology in today's market with an enormous number of applications. Mini UAVs are developed in order to compensate the performance constraints imposed by larger UAVs during emergency situations. Multiple mini autonomous UAVs require communication and coordination for ubiquitous coverage and relaying during deployment. Multi-UAV coordination or swarm optimization is required for reliable connectivity among UAVs, due to its high mobility and dynamic topology. In this paper, a Secured UAV (S-UAV) model is proposed which takes the location of the UAVs as inputs to form a Wireless Mesh Network (WMN) among multiple drones with the help of a centralized controller. After WMN formation, efficient communication takes place using A* search, an intelligent algorithm that finds the shortest communication path among UAVs. Further, the S-UAV model utilizes cryptographic techniques such as Advanced Encryption Standard (AES) and Blowfish to overcome the security attacks efficiently. Simulation results show that the S-UAV model offers higher throughput, reduced power consumption and guaranteed message transmission with reduced encryption and decryption time. [ABSTRACT FROM AUTHOR]

This paper proposes a novel secure channel estimation technique to provide security against leakage of the channel estimates to any malicious user by utilizing artificial noise (AN) along with full-duplex (FD) transmissions. AN overcomes the drawback of FD transmission, where any strategically located eavesdropper can minimize the interference signal received from the FD receiver. The proposed secure channel estimation technique comprises three stages, where the first stage is responsible for the estimation of the residual self-interference (SI) channel. The second stage acquires rough channel estimates to design AN orthogonal to the channel between legitimate transmitter-receiver for the next training stage. In the third stage, both legitimate nodes transmit orthogonal AN signals along with the known training signals using FD transmissions. For power allocation, we have presented a novel local adaptive power allocation algorithm at each legitimate node to allocate the powers to the training signals, and AN signals while ensuring equivocation at the eavesdropper. We provide the mean square error (MSE) to indicate the performance achieved by the respective nodes. We have also provided the bit error rate (BER) simulation analysis to indicate the secure communication achieved by securing the channel estimation process. The presented simulation analysis indicates that the eavesdropper is unable to decode the transmitted information while the legitimate receiver has robustly decoded the transmitted information. [ABSTRACT FROM AUTHOR]

In this paper, we consider the downlink (DL) of a zero-forcing (ZF) precoded extra-large scale massive MIMO (XL-MIMO) system. The base-station (BS) operates with limited number of radio-frequency (RF) transceivers due to high cost, power consumption and interconnection bandwidth associated to the fully digital implementation. The BS, which is implemented with a subarray switching architecture, selects groups of active antennas inside each subarray to transmit the DL signal. This work proposes efficient resource allocation (RA) procedures to perform joint antenna selection (AS) and power allocation (PA) to maximize the DL spectral efficiency (SE) of an XL-MIMO system operating under different loading settings. Two metaheuristic RA procedures based on the genetic algorithm (GA) are assessed and compared in terms of performance, coordination data size and computational complexity. One algorithm is based on a quasi-distributed methodology while the other is based on the conventional centralized processing. Numerical results demonstrate that the quasi-distributed GA-based procedure results in a suitable trade-off between performance, complexity and exchanged coordination data. At the same time, it outperforms the centralized procedures with appropriate system operation settings. [ABSTRACT FROM AUTHOR]

The energy detection technology is recommended in the licensed assisted access (LAA) scheme by 3GPP because of its simplicity and low cost. However, due to its inherent limitation, there may exist imperfect channel detection, which can lead to the decrease of the channel utilization efficiency and the deterioration of fairness. The imperfect detection can generally be represented by the detection probability and false alarm probability, which depend on detection time, signal to noise ration (SNR), sampling rate and energy threshold. However, among the parameters, only the energy threshold can be dominated by LAA small base stations (SBSs) in the LAA scheme. Therefore, the energy threshold should be dynamically adjusted in the changeable channel environment such that the detection accuracy can improved as high as possible. Consider the fact that the optimization theory cannot be used to optimize the energy threshold since the expressions of performance indexes about the energy threshold are extremely complex, a Q-learning based energy threshold optimization algorithm (QLET) is thus proposed in the paper, where LAA SBSs act as the agent, the energy threshold is defined as the agent action, the different combinations of fairness and throughput are defined as the agent states, and the fairness and the reward function are also redefined. In order to ensure the smooth implementation of the proposed QLET algorithm, the information exchange mechanism, where the sending-confirmation mechanism and 1- persistent CSMA are used, is also proposed. Based on the proposed QL framework, the agent can learn the optimal energy threshold by repeatedly interacting with the environment, which enables the coexistence system to obtain the best coexistence performance. A large number of simulation results show that the proposed QLET is superior to the traditional fixed energy threshold scheme (FET) in terms of the fairness, WiFi collision probability and transmission delay, and that QLET is almost the same as FET in term of throughput. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been widely applied for classification tasks in wireless communications such as link scheduling, user association and base station (BS) muting. When training a DNN using datasets with highly-skewed class distribution where most data belong to a few majority classes, learning performance for minority classes will degrade since the imbalanced data forces the training process to be biased towards the majority classes. In many wireless problems, multiple decisions for classification are made jointly, say deciding which BSs in a network should be muted to avoid interference. In this paper, we employ DNN to learn an optimal predictive interference coordination policy, and strive to avoid biased learning in such a multi-label multi-class classification problem. The major contribution is proposing a training method to encourage fairness among classes by minimizing the maximal cost of decisions among classes, which is converted into a problem to optimize the weighting factors on the training cost of each class. We provide a gradient descent algorithm to optimize the weighting factors and the model parameters of the DNN by alternative updates. Simulation results show that the training method can improve the learning performance for the minority class and can achieve higher network utility than existing training methods. [ABSTRACT FROM AUTHOR]