Visual Detection-Based Blockage Prediction for Beyond 5G Wireless Systems

The emergence of sixth-generation (6G) wireless networks is expected to enable ultra-reliable, low-latency communication (URLLC) for mission-critical applications such as autonomous systems, remote healthcare, and industrial automation. However, the increasing complexity, heterogeneity, and dynamic nature of next-generation networks pose significant challenges to conventional network management and optimization techniques. This paper proposes an AI-native self-optimizing architecture designed to address these challenges by embedding artificial intelligence at the core of 6G network operations. Unlike traditional add-on AI solutions, the proposed framework integrates machine learning models directly into the network control plane, enabling real-time monitoring, predictive analytics, and autonomous decision-making. The architecture leverages deep learning, reinforcement learning, and federated learning to dynamically optimize resource allocation, network slicing, interference management, and fault recovery. Furthermore, a digital twin-based network representation is incorporated to simulate and predict network behavior under varying conditions, thereby enhancing reliability and adaptability. The proposed system also emphasizes energy efficiency and scalability by utilizing lightweight AI models and edge intelligence. Simulation-based evaluations indicate significant improvements in network reliability, latency reduction, and spectral efficiency compared to conventional approaches. The results demonstrate that AI-native architectures can effectively transform 6G networks into intelligent, self-evolving systems capable of meeting stringent performance requirements. This work provides a comprehensive foundation for the development of fully autonomous wireless networks and highlights the critical role of artificial intelligence in shaping the future of ultra-reliable communication systems.

5G networks provide technology enablers targeting industrial applications. One key enabler is the Ultra Reliable Low Latency Communication (URLLC). This paper studies the performance impact of network delay on closed-loop control for industrial applications. We investigate the performance of the closed-loop control of an UR5 industrial robot arm assuming fix delay. The goal is to stress the system at the upper limit of the possible network delay. We prove that to achieve the maximum speed, URLLC is a must have.

Ultra-reliable low latency communication (URLLC), which refers to achieving almost 100% reliability at a certain (satisfactory) level of services and stringent latency, is one of the key requirements for 5G networks. However, most prior studies on reliable communication did not address space domain analysis. Neither were they pursued from a dependability perspective. This paper addresses the ultra-reliable communication (URC) aspect of URLLC and aims at advocating the concept of URC from a dependability perspective in the space domain. We perform in-depth analysis on URC considering both the spatial characteristics of cell deployment and user distributions, as well as service requirements. We first introduce the concepts of cell availability and system availability in the space domain, then perform connectivity-based availability analysis by considering a Voronoi tessellation where base stations (BSs) are deployed according to a certain distribution. Moreover, we investigate the relationship between signal-to-interference-plus-noise ratio (SINR), user requirement, and achievable cell or system availability by employing both Poisson point process (PPP) and determinantal point process (DPP) BS distributions. For SINR-based availability analysis, coverage contours are identified. Considering further the user distribution in a region of interest, expressions for system availability are derived from users' perspective. Furthermore, we propose an algorithm which could be used for availability improvement based on the calculated availability level. Numerical results obtained considering diverse network scenarios and cell deployments with multiple cells and multiple topologies illustrate the achievable availability under various circumstances.

The Ultra-Reliable Low-Latency Communication (URLLC) is expected to be an important feature of 5G and beyond networks. Supporting URLLC in a resource-efficient manner demands optimal Modulation and Coding Scheme (MCS) selection and spectrum allocation. This paper presents a study on MCS selection and spectrum allocation to support URLLC. The essential idea is to establish an analytical connection between the delay and reliability requirements of URLLC data transmission and the underlying MCS selection and spectrum allocation. In particular, the connection factors in fundamental aspects of wireless data communication include channel quality, coding and modulation, spectrum allocation and data traffic characteristics. With this connection, MCS selection and spectrum allocation can be efficiently performed based on the delay and reliability requirements of URLLC. Theoretical results in the scenario of a 5G New Radio system are presented, where the Signal-to-Noise Ratio (SNR) thresholds for adaptive MCS selection, data-transmission rate and delay, as well as spectrum allocation under different configurations, including data duplication, are discussed. Simulation results are also obtained and compared with the theoretical results, which validate the analysis and its efficiency.

The booming of the industrial Internet of Things (IIoT) brings an exponential increase in industrial devices, calling for more flexible and low-cost communications. The fifth generation and beyond (B5G) communication technologies provide a dedicated solution by supporting two industry-targeted technologies: Massive machine-type communications (mMTC) and ultra reliable low-latency communications (URLLC). In this article, we design a B5G-aided quality test system in advanced manufacturing, where various sensors are connected to the base station (BS) and send contextual information via mMTC. The BS and quality test machine transmit short length commands and small size feedback to each other, respectively, via URLLC. We formulate a long-term optimization problem to improve the product qualification rate by maximizing the expected average reward with limited testing capacity and changing configurations. To address this problem, we develop a novel context-aware combinatorial quality test (CC-QT) algorithm based on bandit learning (BL), which integrates contextual information to predict the product quality, and a combinatorial method to decrease the complexity of the BL process. Furthermore, we derive a performance upper bound of the proposed CC-QT and analyze its computational complexity. Experimental results illustrate the performance of CC-QT and substantiate its superiority over the existing algorithms.

5G wireless networks aim to achieve seamless mobile broadband services, machine to machine and ultra-reliable low latency communications. These goals require massive improvements in terms of capacity, reliability, latency reduction, and scalability. Besides software defined networks and network function virtualization, self organizing networks (SON) is another enabling technology which makes 5G feasible. Automatic neighbor relations (ANR) is a prominent component of SON which has direct impact on reliability, scalability, and capacity of the wireless networks. When the current state of standardization and implementation of ANR functionality is considered, it is seen that a new approach is needed for ANR to comply with 5G requirements. Thus, in this paper a comprehensive hybrid ANR (H-ANR) architecture which leads to the management of relations utilizing an extensive set of universal performance criteria, configuration metrics, and measurements is proposed. The H-ANR functionality ranks the neighbors not based on instantaneous information but on historic values of the performance criteria and other metrics. The attributes of distributed ANR (D-ANR) module is also managed by H-ANR to prevent the repetitive addition of unwanted neighbors via D-ANR or X2 interface. Performance of the proposed H-ANR functionality is also compared with the case when only D-ANR is available on a Long Term Evolution Advanced network.

We investigate a heterogeneous network (HetNet) including sub-6GHz base stations (BSs), mmWave BSs, and THz BSs to support enhanced mobile broadband (eMBB) users and ultra-reliable low-latency communication (URLLC) users. We particularly investigate a user-centric network in which the users locally and dynamically select and switch among BSs over time to achieve their highest utility. Two types of users have different Quality of Service (QoS) requirements. Thus, we design two types of utility functions specifically for the eMBB users and URLLC users. Then, to model the dynamic selection behavior of the users, we propose to use a fractional game with the power-law memory. The fractional game allows the eMBB users and the URLLC users to incorporate their past strategies into their current selection, thus improving their utility. Furthermore, we consider the case that the BSs communicate the system state with each other, and we model the network selection of the users as a multi-agent problem. Then, we propose to use a multi-agent deep reinforcement learning (MADRL) algorithm that enables the URLLC users and eMBB users to make their network selection decision online to achieve their long-term utility. Various simulation results are provided to demonstrate the scalability and effectiveness of the proposed approaches. Particularly, compared with the classical game, the fractional game is able to achieve a higher utility but incurs a higher network adaptation cost. Moreover, the different types of URLLC users (in terms of latency and reliability requirements) and the number of URLLC users in the network significantly affect the total utility and the network selection strategies of the eMBB users. Importantly, given the full observations, the MADRL outperforms both classical and fractional games in terms of total network utility.

A digital twin (DT) framework for Internet‐of‐thing (IoT) networks is proposed where unmanned aerial vehicles (UAVs) acting as flying mobile edge computing (MEC) servers support the task offloading on the fly. The considered DT model is very well suitable for industrial automation with the strict constraints of mission‐critical services' ultra‐reliable low‐latency communication (URLLC) links. To support low‐latency IoT devices, we formulate the end‐to‐end (e2e) latency minimisation problem of digital twin‐aided offloading UAV‐URLLC. Specifically, the minimised latency is obtained by jointly optimising both communication and computation parameters, namely power, offloading factors, and the processing rate of IoT devices and MEC‐UAV servers. Due to the highly non‐convex optimisation problem, we first consider the K‐means clustering algorithm to optimally deploy the on‐demand UAVs. Then, an alternative optimisation approach combined with appropriate inner approximations is effectively exploited to tackle this challenge. We demonstrate the effectiveness of the proposed DT framework through representative numerical results.

The quality of collision detection algorithm directly affects the performance of the whole simulation system. To address the low efficiency and low accuracy in detecting the collisions of flexible cloths in virtual environments, this paper proposes an oriented bounding box (OBB) algorithm with a simplified model, tree structure for a root-node double bounding box, and continuous collision detection algorithm incorporating an OpenNN-based neural network optimization. First, for objects interacting with the cloths with more complex modeling, the model is simplified with a surface simplification algorithm based on the quadric error metrics, and the simplified model is used to construct an OBB. Second, a bounding box technique commonly used for collision detection is improved, and a root-node double bounding box algorithm is proposed to reduce the construction time for the bounding box. Finally, neural networks are used to optimize the continuous collision detection algorithm, as neural networks can efficiently process large amounts of data and remove disjoint collision pairs. An experiment shows that the construction of an OBB using the simplified model is almost identical to that of the original model, but the taken to construct the OBB is reduced by a factor of approximately 2.7. For the same cloth, it takes 5.51%–11.32% less time to run the root-node double bounding box algorithm than the traditional-hybrid bounding box algorithm. With an average removal rate nearly identical to that of the traditional filtering method, the elapsed time is reduced by 7%–11% by using the continuous collision detection algorithm based on an OpenNN neural network optimization. The simulation results are realistic and in line with the requirements for real-time cloth simulations.

Base station location selection and network optimization are critical to improving the performance of wireless communication networks in terms of latency reduction. To this end, the article proposes leveraging a convolutional neural network (CNN) to improve the accuracy of base station location selection and network latency reduction. The CNN method, based on a three-dimensional representation including signal strength data set, network topology data set, and transmission path data set, is used to select base station location and optimize the multihop relay network for latency reduction. The article presents a following method: location selection and network optimization for the wireless communication network. First, it collects the experimental data set of base station location selection and network optimization, and then uses the training data to train the CNN model to extract features. Once the training is done, the article further optimizes the network parameters and configurations, and ultimately obtains the optimal base station location and network configuration while minimizing network latency. As a result, simulation results indicate that the CNN model has remarkable performance in base station location selection, as well as in network optimization. In summary, the feature extraction and processing ability of CNN are powerful, enabling it to effectively capture factors leading to delay, hence improving the performance of base station location selection and network optimization. The article also demonstrates that the CNN model can be adjusted according to different environments and scenario settings through dynamic tuning.

Ensuring ultra-low latency and high reliability in 6G network slices remains a significant challenge, as current NFV orchestration approaches are largely reactive and not designed to anticipate performance degradation. The advent of 6G networks brings forth stringent requirements for ultra-reliable low-latency communication (URLLC), necessitating advanced orchestration mechanisms that go beyond reactive policies in traditional NFV environments. In this paper, we propose a latency-aware, AI-driven NFV slice orchestration framework aligned with ETSI MANO architecture to address the needs of time-sensitive 6G applications. Our framework integrates a predictive AI engine into the NFV Orchestrator (NFVO) to forecast latency violations based on real-time telemetry and historical trends. It enables dynamic scaling, intelligent VNF migration, and infrastructure-level isolation to maintain stringent end-to-end (E2E) latency targets. Experimental results indicate up to 30% reduction in average latency, a 42% improvement in SLA compliance, and 25% lower migration overhead compared to traditional reactive orchestration. The framework provides a scalable and intelligent orchestration solution adaptable to future 6G deployments.

Vehicle detection in aerial images is an important and challenging task in the field of remote sensing. Recently, deep learning technologies have yielded superior performance for object detection in remote sensing images. However, the detection results of the existing methods are horizontal bounding boxes that ignore vehicle orientations, thereby having limited applicability in scenes with dense vehicles or clutter backgrounds. In this article, we propose a one-stage, anchor-free detection approach to detect arbitrarily oriented vehicles in high-resolution aerial images. The vehicle detection task is transformed into a multitask learning problem by directly predicting high-level vehicle features via a fully convolutional network. That is, a classification subtask is created to look for vehicle central points and three regression subtasks are created to predict vehicle orientations, scales, and offsets of vehicle central points. First, coarse and fine feature maps outputted from different stages of a residual network are concatenated together by a feature pyramid fusion strategy. Upon the concatenated features, four convolutional layers are attached in parallel to predict high-level vehicle features. During training, task uncertainty learned from the training data is used to weight loss function in the multitask learning setting. For inferencing, oriented bounding boxes are generated using the predicted vehicle features, and oriented nonmaximum suppression (NMS) postprocessing is used to reduce redundant results. Experiments on two public aerial image data sets have shown the effectiveness of the proposed approach.

The benefits of the currently evolving IEEE Time-Sensitive Networking (TSN) standard have already been globally recognized. Whereas the application of TSN in a LAN is currently widely and globally tested, TSN in a Metropolitan Area Network (MAN) has not been a major focus until now. The possible benefits of utilizing co-located Edge Clouds in order to support multiple urban production sites with industrial realtime applications open a wide range of new business models. Therefore, we have analyzed the feasibility of transparently using PROFINET over TSN via a Dense Wavelength Division Multiplex (DWDM) link, where a machine park is controlled remotely by an Edge-based virtual Programmable Logic Controller (vPLC). As a result, we are able to setup a TSN connection over a MAN with a one-way delay of about 156.5 J.μs and a jitter of about 12 ns. This work can be extended to allow for dynamically provisioned TSN flows and multi-path Frame Replication and Elimination (FRER) for distributed hard real-time machine control and adoption to Ultra-Reliable Low-Latency Communication (URLLC) 5G campus networks.

Industrial automation, Augmented Reality (AR), Virtual Reality (VR), Robotics, and many other applications need accurate time and data delivery with strict deadlines. The IEEE 802.1 Time-Sensitive Networking (TSN) group defines a set of tools for deterministic communication with high reliability. Although TSN has started from wired (Ethernet) networks, the newer generation wireless technologies, especially Wi-Fi 6/6E and 5G, offer capabilities to extend and enhance TSN operation over the wireless medium. The 3rd Generation Partnership Project (3GPP) Release 16 supports Ultra-Reliable Low-Latency Communications (URLLC) and introduces the capabilities for integrating 5G with TSN networks motivated by the requirements of time-critical industrial systems. This paper presents and evaluates an industrial control system enabled by 5G and TSN capabilities. We describe a TSN over 5G testbed developed with 3GPP Release 15 hardware and discuss the measurement methodology along with Key Performance Indicators (KPIs) required for meeting timing requirements for an industrial control application. We also explore the configuration of TSN over 5G systems and methodologies needed to characterize the Quality of Experience (QoE) for industrial use cases.

The need for latency reduction has recently spurred interest in short block length transmissions over wireless channels. In this paper, the performance of this type of transmissions is analyzed in the presence of multi-variate stationary Rayleigh fading coherent channels. The channel model is inspired in multi-symbol OFDM transmissions for ultra-reliable low latency communication (URLLC) services, according to which information is sent in a small number of OFDM symbols to reduce latency. More specifically, a high SNR approximation of the ergodic capacity and channel dispersion is derived for this particular fading choice. Results show that the optimum performance depends on the time-frequency fading dynamics through very simple functions of the channel correlation coefficients. The derived formulas provide a very useful tool to design physical layer system parameters from information measured at the receiver, as illustrated in a simple example where a HARQ system is studied in this asymptotic regime.