Communication networks are in constant evolution to adapt to the ever-changing demands of modern services and applications. On the one hand, technologies within the framework of the fifth generation of communication networks (5G), currently in a steady course towards 6G, are being designed with unprecedented performance and flexibility capabilities to empower the digital transformation of heterogeneous vertical industries. On the other hand, Time-Sensitive Networking (TSN) is being developed to enable converged network infrastructures able to satisfy the most stringent communication requirements in regards to bounded low latency and reliability. In verticals such as manufacturing, a joint usage of 5G and TSN is very promising to enable revolutionary use cases that coexist with the constraints imposed by industrial communications and systems. In this paper, we exhaustively survey the technology landscape concerning the integration between 5G and TSN technologies, including the perspectives of both industry and academia. In the first part of this paper, we provide a comprehensive review of relevant standards and outcomes from industry initiatives. We first examine the capabilities provided by TSN and their application to industrial communications. Likewise, we contextualize the 5G architecture and its key enabling technologies, and later provide a comprehensive review of the architecture and mechanisms to enable the integration between TSN and 5G. In the second part of this paper, we extensively survey the state of the art from academic literature concerning proposals that contribute to enabling, improving, and/or demonstrating different aspects of the integration or interworking between 5G and TSN technologies.

Industrial networks are introducing Internet of Things (IoT) technologies in their manufacturing processes in order to enhance existing methods and obtain smarter, greener and more effective processes. Global predictions forecast a massive widespread of IoT technology in industrial sectors in the near future. However, these innovations face several challenges, such as achieving short response times in case of time-critical applications. Concepts like in-network computing or edge computing can provide adequate communication quality for these industrial environments, and data plane programming has been proved as a useful mechanism for their implementation. Specifically, P4 language is used for the definition of the behavior of programmable switches and network elements. This paper presents a solution for industrial IoT (IIoT) network communications to reduce response times using in-network computing through data plane programming and P4. Our solution processes Message Queuing Telemetry Transport (MQTT) packets sent by a sensor in the data plane and generates an alarm in case of exceeding a threshold in the measured value. The implementation has been tested in an experimental facility, using a Netronome SmartNIC as a P4 programmable network device. Response times are reduced by 74% while processing, and delay introduced by the P4 network processing is insignificant.

The aim of this paper is to present an architecture to support reconfigurable multimedia services for a practical emergency environment use case of rescue operations. Specifically, radio communication and video surveillance services are provided by means of a small device carried by a mobile vehicle. This solution is validated by implementing a digital mobile radio (DMR) standard radio hotspot and a video streaming server in an unmanned aerial vehicle (UAV) that conveys a device with scarce resources in order to minimize power consumption. To achieve a fast and flexible deployment of the envisioned services, a virtualization-based approach is proposed. Namely, a Kubernetes orchestrator is used to manage the life-cycle of services deployed on a small resource device, endowing the architecture with scalability and management flexibility. This paper describes the executed performance tests that measured key parameters such as deployment time and recovery time after disconnection. Highly promising results were obtained, showing that the proposed architecture can be deployed in less than 4 minutes and can recover from network disconnections in less than 10 seconds. Thus, the performance, reliability and flexibility of the overall solution are demonstrated.

At present, there is growing interest in automated biometric identification applications. For these, it is crucial to have a system capable of accurately identifying a specific group of people while also detecting individuals who do not belong to that group. In face identification models that use Deep Learning (DL) techniques, this context is referred to as Open-Set Recognition (OSR), which is the focus of this work. This scenario presents a substantial challenge for this type of system, as it involves the need to effectively identify unknown individuals who were not part of the system’s training data. In this context, where the accuracy of this type of system is considered crucial, selecting the model to be used in each scenario becomes key. It is within this context that our work arises. Here, we present the results of a rigorous comparative analysis examining the precision of some of the most widely used models today for face identification, specifically some Convolutional Neural Network (CNN) models compared with a Vision Transformer (ViT) model. All models were pre-trained on the same large dataset and evaluated in an OSR scenario. The results show that ViT achieves the highest precision, outperforming CNN baselines and demonstrating better generalization for unknown identities. These findings support recent evidence that ViT is a promising alternative to CNN for this type of application.