Non-Terrestrial Networks (NTNs) play a critical role in ensuring uninterrupted communication services. Reliable communication between launch vehicles and ground stations is a cornerstone of mission-critical telemetry, tracking, and command (TT&C) systems. During high-dynamic phases such as ascent, main engine cutoff, serial staging, and re-entry burns, traditional ground-based antennas often encounter reduced signal quality due to rapidly changing elevation angles, Doppler effects, and terrain obstructions. These effects are exacerbated over oceanic re-entry zones, where terrestrial coverage is limited. To address this issue, this study proposes the integration of aerial vehicles (AVs) as the aerial segment, forming an Air-Ground Integrated Network (AGIN). AVs leverage their flexibility and ability to transmit via line-of-sight (LoS), act as wireless relay stations, effectively enhancing rocket signal transmission and improving Quality of Service (QoS), and agile relaying of communication signals. In this work, we explore a low-based airborne relay system capable of dynamically adjusting its position to maintain a reliable communication link with the rocket and forward the signal to a terrestrial base station (TBS). Next, we employ Deep Reinforcement Learning (DRL) techniques to optimize the UAV 3D position. Simulation results demonstrate that this approach significantly improves the network communication efficiency, providing essential theoretical foundations and technical references for achieving reliable and efficient SAGIN systems.

This paper proposes an integrated low Earth orbit (LEO) satellite and unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) framework that exploits the dual functionality of sensing and communication, enabling efficient detection of fish school zones and real-time data transmission to fishing vessel users in marine environments. This study focuses on two key components within the proposed framework: first, UAVs equipped with sensing radar perform fish school detection in marine environments by employing a region-based Vision Transformer (ViT) algorithm, using echo signals that are converted into range-doppler maps (RDMs). Second, to enhance system performance by addressing the challenges posed by UAV mobility and the need for adaptive beamforming, we formulate a joint optimization problem for UAV trajectory and beamforming. This problem is addressed using the proximal policy optimization (PPO) algorithm combined with the ViT model referred to as PPO-ViT, which incorporates the ViT detection results as part of the state input to guide optimal UAV trajectory planning and beamforming strategy. Simulation results demonstrate that the ViT-based detection achieves superior accuracy compared to other CNN models, while the PPO-ViT framework significantly improves average data rate and sensing precision over baseline methods.

Non-Terrestrial Networks (NTNs) play a critical role in ensuring uninterrupted communication services during emergencies. However, in dense urban environments, complex propagation conditions, such as obstructions from buildings, significantly degrade the link performance between satellites and ground users. To address this issue, this study proposes the integration of Drone Base Stations (DBSs) as the aerial segment and Reconfigurable Intelligent Surfaces (RISs) as the ground segment within satellite communication networks, forming a space-air-ground integrated network (SAGIN). DBSs leverage their flexibility and ability to transmit via line-of-sight (LoS), act as wireless relay stations, effectively enhancing the satellite signal transmission and improving the quality of service (QoS). Meanwhile, RIS significantly enhances the strength of reflected signals by dynamically adjusting the amplitudes and the phases, enabling stable and efficient communication networks. This study employs a deep reinforcement learning (DRL) techniques to optimize the 3D DBS position and RIS phase configurations, based on the dynamic spatial distribution of ground users. Simulation results demonstrate that this approach significantly improves network throughput and communication efficiency, providing essential theoretical foundations and technical references for achieving reliable and efficient SAGIN systems.

The marine IoT (MIoT) has experienced widespread adoption in the maritime industry; however, its communication infrastructure faces significant challenges due to a lack of terrestrial networks and the dynamic nature of oceanic environments. In response, low-Earth orbit (LEO) satellites have been suggested as an alternative solution. However, LEO satellites also face limitations, including coverage gaps due to the power constraints of MIoT devices (MIoTDs) and the curvature of the Earth, which impede continuous connectivity. To address these challenges, integrating uncrewed aerial vehicles (UAVs) as aerial base stations between LEO satellites and MIoTDs has gained attention as an effective solution to enhance communication. Managing UAV mobility and ensuring reliable communication requires autonomous 3-D trajectory optimization and dynamic resource allocation. This article presents an integrated LEO and multi-UAV-enabled MIoT network designed to maximize communication coverage, system throughput, and fairness. To achieve this, we formulate a joint UAV trajectories and resource allocation (UTCRA) optimization problem. To address the UTCRA problem, we propose a two-stage learning approach: 1) Gaussian mixture models (GMMs)-based clustering is initially applied to dynamically cluster MIoTDs under different UAVs, ensuring a balanced distribution of user loads among UAVs. 2) A federated multiagent deep deterministic policy gradient (FL-MADDPG) algorithm is employed to continuously optimize UTCRA, thereby enhancing communication efficiency. Simulation results demonstrate that FL-MADDPG with GMM significantly enhances communication coverage, average throughput, and fairness. It outperforms benchmark algorithms across all evaluated metrics, highlighting its strong potential as a method for next-generation MIoT networks.

The rapid expansion of wireless communication mandates the development of efficient and computationally light solutions for base station deployment. Despite the manifold advantages of the latest 5G networks, challenges such as limited coverage and signal attenuation persist, underscoring the need for swift and precise estimation of base station coverage. To address this imperative, this paper introduces a deep learning-based indoor channel prediction model. Through comparative analysis with a traditional high-precision ray-tracing model, the paper showcases the computational prowess of the proposed deep-learning model. Once trained, it achieves an impressive 99.7% reduction in computation time while maintaining comparable accuracy to the ray-tracing model. The proposed method promises expedited and accurate evaluation of optimal base station placements, particularly beneficial for indoor networks such as 5G small cells or wireless LAN. By integrating into handheld platforms, users can swiftly input indoor layouts and base station locations to obtain signal coverage. Such integration not only reduces power consumption but also drives advancements in energy-efficient practices within telecommunication infrastructure.

Abstract This paper presents a path loss model based on path profile in urban propagation environments for 5G systems. Although deep learning approaches are indeed powerful in tasks involving prediction or classification, they often lack transparency and suffer from high computational complexity. The proposed model combines the log‐distance path loss model for line‐of‐sight propagation scenarios and a machine‐learning‐based model for non‐line‐of‐sight (NLOS) cases. This paper uses the principal component analysis algorithm to extract relevant features out of some selected attributes of the path profile for NLOS cases. Then, the path loss model can be constructed based on the approach of polynomial regression. Simulation results show that the proposed model outperforms the conventional models when operating in the 3.5 GHz frequency band. The standard deviation of prediction error was reduced by about 22.2–37.2% dB when compared to the conventional models. Furthermore, the prediction performance was also evaluated in a non‐standalone 5G New Radio network in the urban environment of Taipei city. The real‐world measurements show that the standard deviation of prediction error can be reduced by 3.33–6.13 dB when compared to the conventional models.

Over the last few years, drone base station (DBS) technology has been recognized as a promising solution to the problem of network design for wireless communication systems, due to its highly flexible deployment and dynamic mobility features. This article focuses on the 3-D mobility control of the DBS to boost transmission coverage and network connectivity. We propose a dynamic and scalable control strategy for drone mobility using deep reinforcement learning (DRL). The design goal is to maximize communication coverage and network connectivity for multiple real-time users over a time horizon. The proposed method functions according to the received signals of mobile users, without the information of user locations. It is divided into two hierarchical stages. First, a time-series convolutional neural network (CNN)-based link quality estimation model is used to determine the link quality at each timeslot. Second, a deep$Q$-learning algorithm is applied to control the movement of the DBS in hotspot areas to meet user requirements. Simulation results show that the proposed method achieves significant network performance in terms of both communication coverage and network throughput in a dynamic environment, compared with the$Q$-learning algorithm.

Vehicles are one kind of human’s transport tools that can carry us to anywhere. Safety is an important issue for vehicle applications. Tire is an important element of the vehicle, because the vehicle only has four points connect on the road through tires. Many accidents are caused the tire problems. There are more and more researches in intelligent tire base on safety issues. Tire pressure monitor system (TPMS) can be called an application of intelligent tires that are currently a very popular tire monitoring device, it provides pressure and temperature information for drivers. The information can let drivers understand their tire’s status through simple information. Not only pressure and temperature can affect safety, but also tire’s use mileage. The tire wear has some relation to safety. The mileage has been defined by tire spec. The different tires have different specs and the tire wear status cannot be defined clearly. The wear status is hard to get that is because the vehicle condition, use scenario and situation are complicated. Drivers can’t understand how many miles did the tire use and what status the tire. This paper proposed a method to estimate and monitor tire mileage and wear base on simple sensors. G-sensor and hall sensors are common sensors in applications. The method will use these simple sensors to implement the method. Drivers can accord information to evaluate the tire status and decide the timing to replace the tire. It can help drivers to increase safety during the drive and provide a solution to support intelligent tire function.

Many Internet-of-Things (IoT) services rely on location information. This article proposes a deep learning-based fingerprinting outdoor positioning scheme (DFOPS) for use in scalable environments. The proposed scheme is a hierarchical combination of the support vector machine (SVM) and long short-term memory (LSTM) algorithms. It was applied in a large-scale wireless environment with multiple wireless local area networks (WLANs) and cellular base stations. The results show that the positioning error of the proposed scheme is 42 cm, and the computation time is reduced by 63% compared with conventional methods. Thus, the proposed system can provide promising and reasonable support location-aware services for IoT devices in large-scale wireless environments.

Mobile users are interested in utilising high network capabilities without time and place constraints. However, with a high level of interest in the usage of mobile phones and internet facilities, the limited capacity of terrestrial base stations (BSs) is unbalanced. As a potential alternative to BSs, unmanned aerial vehicles (UAVs) are emerging as a means of transmitting wireless data to ground mobile users. As an air‐to‐ground communication network, the real UAVs deployed and collected communication data from ground mobile users. The main objective of this study is to analyse and evaluate user throughput, interference, and power transmission when the UAVs are at different heights. The parameters used include the locations of the UAVs and users, the altitudes and elevation angles from the users to UAVs, signal‐to‐noise‐ratio, throughput values, the categories of line‐of‐sight, and non‐line‐of‐sight links. Furthermore, K ‐means used as a clustering method for class identification, long short‐term memory (LSTM), and gated recurrent unit (GRU) to analyse and evaluate system performance. The system's performance was compared with a multi‐layer perceptron approach. The evaluation results show that the proposed LSTM–GRU provides reliable and encouraging performance with low computational complexity, which is appropriate for heterogeneous networks.

Deploying femtocells faces a major challenge of causing downlink interference to the existing macrocell. This paper proposes an intelligent spectrum sharing mechanism for a two-layer cellular network, which comprises macrocells and femtocells. Because users are scheduled to access the spectrum in time-domain according to their channel conditions, the usage of spectrum is predictable by tracing the channel conditions. Therefore, the femtocell can be managed, in time-domain, to reconfigure the antenna radiation pattern in order to suppress the interference to closely-located macrocell users who are expecting to access the spectrum. Simulation results show that user throughput at the macrocell edge can be boosted by 83%, compared to deploying femtocells with fixed omni-directional antennas.

Frequency-selective fading and inter-carrier-interference (ICI) are two fundamental issues that should be dealt with before adopting orthogonal frequency division multiplexing (OFDM). Instead of using complex designs for exploiting frequency diversity and cancelling ICI, this paper explores how spreading signal, on either frequency-domain or time-domain, can improve the performance of OFDM systems. Based on the carrier interferometry technique, information symbols are spread over all the OFDM subcarriers to pursue frequency diversity. Then a packet retransmission scheme, which can be seem as spreading signal in time-domain, is proposed to suppress ICI. Numerical simulations show that frequency diversity can be pursued by spreading information symbols in OFDM subcarrier domain and that ICI can be suppressed by spreading packets in time domain. As a result, an enhanced OFDM system with low complexity signal spreading can be delivered.

This paper explores multiuser downlink beamforming in a distributed manner, where each user locally and sequentially optimizes its own beamforming phase and amplitude according to some performance measures. For phase optimization, the complex non-convex optimization problem is reformulated into a convex one. Given the optimal phase, the amplitude is pursued through the method of Lagrange multiplier. Our numerical simulations demonstrate that the proposed algorithm matches the conventional centralized two-user zero-forcing beamforming performance in terms of bit error rate. Meanwhile, our method utilizes 50% less feedback as compared to the conventional one. As a result, a low complexity distributed multiuser beamforming is delivered.

Spatial division multiple access can be used to boost spectrum efficiency if perfect channel information is available at the transmitter. By using equal-gain beamforming, this paper reformulates the difficult non-convex optimization problem of finding the optimal multiuser beamforming vectors into a convex one. Consequently, the Nash equilibrium solution can be reached based on a non- cooperative game, where each receiver feedbacks its selected beamforming vector without sharing information with the others. This paper verifies the performance over spatial correlated, multipath, time-varying Rayleigh fading channels for downlink orthogonal frequency division multiplexing systems. Based on long-term beamforming, the proposed algorithm outperforms the conventional approach in terms of received SINR, besides the reduced complexity.

In recent years, multi-cell downlink (DL) collaborative multi-input multi-output (MIMO) transmission has drawn a lot of attentions due to its potential benefits in system throughput. However, the requirements on training and feedback may hamper its practical applications. In this paper, we consider a single-user collaborative random beamforming (Co-RBF) scheme to ease the training and feedback burden in a multi-cell environment. The proposed single-user collaborative random beamforming system, either with and without additional transmitter phase adjustments, are described and analyzed from outage probability perspective. From analysis and numerical results, collaborative random beamforming schemes can provide macro diversity gain with little feedback. This implies its feasibility for limited feedback collaborative wireless systems.

Worldwide interoperability for microwave access (WiMAX) suffers from inter-carrier interference (ICI) since it adopts orthogonal frequency division multiplexing in physical layer. This study applies a repetition coding scheme, which encodes the same data on a subcarrier pair, to the hierarchical modulation to suppress the ICI and thus the inter-layer interference. Consequently, the proposed method mitigates the effects of fading and interference and provides a finer granularity of modulation order for link adaptation. Besides, the repetition coding scheme is also applied to a hybrid automatic repeat request (HARQ) protocol to recover error packets because of poor channel conditions. The proposed method incorporates the ICI cancellation into the conventional incremental redundancy HARQ and automatically activates the cancellation of ICI without Doppler shift/mobility estimation. Simulations show that the proposed algorithms outperform the conventional schemes in time-varying Rayleigh fading channels, especially in high-mobility environments.

Hierarchical modulation provides layered transmission and is a very promising mechanism to reliably provide basic services to receivers with various reception conditions. Because the high priority layer is allocated with more power, the low priority layer is vulnerable to noise and interference. This paper applies a repetition coding to either of the layers of hierarchical modulation to cancel the inter-carrier-interference, and thus the inter-layer-interference. More importantly, the proposed scheme provides a finer granularity of modulation order, which makes it more flexible to support various radio resource allocation.

Based on the principle of spread spectrum systems, this paper presents a hybrid automatic-repeat-request (HARQ) scheme with the mitigation of intercarrier interference (ICI) by orthogonally encoding transmitted signals on subcarriers for orthogonal frequency division multiplexing (OFDM) systems. The proposed scheme not only increases the signal-to-noise ratio (SNR) but also reduces the ICI. Simulations demonstrates that it outperforms the conventional Chase Combining HARQ in terms of uncoded bit error rate (BER) with nearly no complexity increase.

A signal attenuation difference of arrival (SADOA) scheme is proposed to combine with the time difference of arrival (TDOA) method for mobile location estimation. On the basis of ratio of distances between the mobile and base stations derived from differences of signal attenuations, each SADOA measurement yields a circle on which the mobile may lie. Meanwhile, each TDOA measurement defines a hyperbola on which the mobile may reside. The proposed hybrid SADOA/TDOA scheme uses Taylor-series expansion to linearise the circles and hyperbolas and iteratively computes the mobile position based on least-squares estimation. Without perfect path loss modelling and hardware modification, the proposed scheme reduces location errors compared with either technique separately. Simulations demonstrate encouraging performance with 50% improvement over the conventional TDOA method in shadowing and non-line-of-sight propagation environments.

Propagation delay spread and inter-symbol interference impact the transmission performance of WLAN systems. This paper presents performance enhancement using beamforming techniques operated at the access point. The performance by using omni-directional, switched beam system and phase array system in an indoor office are analyzed and compared. Based on the IEEE 802.11a physical layer specification, numerical simulations indicate that adopting directional antennae at the access point can increase diversity gain in non-line-of-sight propagations channels, while the packet error rate remains below 10-2. Besides, this paper also presents a link adaptation algorithm, based on the Ricean k-factor and signal to noise ratio, for throughput enhancement in IEEE 802.11a systems. Simulation results show that the average throughput reaches 33.7 Mbps in the signal-strength-based conventional algorithm, but rises to 43.1 Mbps when adopting the proposed scheme

Intersystem handover is essential for seamless communication since subscribers move between different systems. This paper proposes an efficient GSM/WCDMA intersystem handover decision based on user mobility to suppress the ping-pong effect. By using GPS positioning, the proposed algorithm adjusts the power threshold associated with distance between the mobile and surrounding base stations. The performance was verified by applying the proposed method to an existing network in urban Taipei city. The results show that the proposed algorithm outperforms traditional method by decreasing the number of intersystem handover and increasing the data throughput

This paper proposes SADOA scheme to combine with TDOA method for mobile location estimation. Based on the ratio of distances between the mobile and base stations derived from differences of signal attenuations, each SADOA measurement yields a circle on which the mobile may lie. Meanwhile, each TDOA measurement defines a hyperbola on which the mobile may reside. The proposed hybrid SADOA/TDOA scheme uses Taylor-series expansion to linearize the circles and hyperbolas and iteratively computes the mobile position based on least-squares estimation. Without perfect path loss modeling and hardware modification, the proposed scheme reduces location errors compared with either technique separately. Simulations demonstrate encouraging performance with 50% improvement over the conventional TDOA method in shadowing and non-line-of-sight propagation environments.

Handover is essential for seamless communication since subscribers move from cell to cell. This paper proposes an efficient handover decision based on user mobility to suppress the ping-pong effect. By using GPS positioning, the proposed algorithm adds a hysteresis parameter associated with distance between the mobile and surrounding base stations and a hysteresis parameter associated with the mobile heading direction in Event 1A and 1C. The performance was verified by applying the proposed method to a WCDMA system in urban Taipei city. The result shows that by using proposed algorithm, handover number and mean active set number are decreased compared to the traditional algorithm.

The variation of signal strength caused by shadowing is a random process, and handover decision mechanisms based on measurements of signal strength induce the "ping-pong effect". The paper proposes an improved handover algorithm, which identifies the correlation among shadowing components based on an estimation of mobile velocity, to suppress the ping-pong effect. The impact of velocity estimation errors on handover performance is investigated. Simulation results indicate that the proposed approach can reduce the number of unnecessary handovers by 9-17% compared to the conventional method, while the signal outage probability remains similar.

When a mobile station moves, the path loss and shadow fading contribute to the large-scale variation in the received signal strength. The variation of signal strength caused by shadow fadings is a random process, and handover decision mechanisms based on measurements of signal strength induce the "ping-pong effect." This paper proposes an improved handover algorithm, based on the estimates of location and velocity of the mobile station, to suppress the ping-pong effect in cellular systems. A practical approach based on GSM measurement data is used to estimate the location and velocity of mobile station to identify the correlation among shadowing components. The impact of location errors on handover performance was examined, and the proposed handover algorithm was applied to a real GSM system in urban Taipei city. The results indicate that the number of unnecessary handover can be reduced 18-26 percent by the proposed approach compared to the conventional method, while the signal outage probability remains similar. Besides, the computational complexity of the proposed algorithm is low, and the algorithm does not use a database or lookup table.

This work presents a cell planning scheme using the genetic algorithm with the help of the propagation model and digitized building information to achieve the acceptable solutions based on impact of background noise for the WCDMA systems. Among these solutions, the best one is selected by a performance simulation platform with a RAKE receiver, which evaluates the BER performance with delay profiles obtained from ray-tracing simulator. The required coverage and maximum throughput can be achieved with the optimum solution for base station number, locations, antennas heights, and transmitting power. Thus, an easy and efficient cell planning for WCDMA systems in the initial stage of system development could be delivered.

This paper proposes a mobile location estimation and tracking technique for wireless communication systems. The location estimation is based on the differences of downlink signal attenuations, which are used to determine circles composed by possible mobile locations. Then the actual location is given by the intersection of the circles. The great advantages of this method are the non-necessity of a known and accurate path loss modelling and the reduction of shadowing effect. Furthermore, a mobile tracking technique via piecewise linear optimization using a simple genetic algorithm is applied to improve the locations estimation. As the results are shown, the estimation errors are much smaller than the errors from cell-ID method in a real GSM system.