Pasar al contenido principal

REDES 6G DETERMINISTAS SEGURAS CON IA NATIVA PARA ENTORNOS HIPERCONECTADOS

PID2022-137329OB-C41

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 46
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Optimized provisioning technique of future services with different QoS requirements in multi-access edge computing

  • Ssemakula, John Bosco|||0000-0002-5457-2640
  • Gorricho Moreno, Juan Luis|||0000-0002-6280-1546
  • Kibalya, Godfrey Mirondo|||0000-0002-7053-3756
  • Serrat Fernández, Juan|||0000-0002-4551-9880
With the present trend towards the use of microservices instead of monolithic software, future applications with diverse computational and delay-sensitive requirements, such as virtual reality (VR) or holographic communications (HC), will be redesigned based on loosely coupled microservices due to their more efficient deployment according to available resources. However, it remains a big challenge to provide such services under stringent quality of service (QoS) requirements at minimum time and cost and with an efficient utilization of the network. Presently, multi-access edge computing (MEC) has been proposed as a promising alternative to deploy future microservice-based applications to achieve faster response times while reducing the overall network load. However, network conditions, edge nodes state and service requests are dynamic, increasing the difficulty for the provisioning of services by MECs. In this context, we propose an optimization deployment heuristic (ODA) to obtain sub-optimal deployments in reasonable time, meeting the requirements of some representative future applications under study. In particular, according to latency requirements, there will be delay-tolerant and delay-sensitive applications, playing a major role regarding the alternatives for the deployment onto single or multiple MEC systems. The evaluation analysis shows that our proposal performs significantly better than other benchmark solutions in most of the metrics used for the experiments, especially in minimizing deployment costs in minimal time.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Cost-effective power management for smart homes: innovative scheduling techniques and integrating battery optimization in 6G networks

  • Riad Al-taie, Rana
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
This paper presents an Optimal Power Management System (OPMS) for smart homes in 6G environments, which are designed to enhance the sustainability of Green Internet of Everything (GIoT) applications. The system employs a brute-force search using an exact solution to identify the optimal decision for adapting power consumption to renewable power availability. Key techniques, including priority-based allocation, time-shifting, quality degradation, battery utilization and service rejection, will be adopted. Given the NP-hard nature of this problem, the brute-force approach is feasible for smaller scenarios but sets the stage for future heuristic methods in large-scale applications like smart cities. The OPMS, deployed on Multi-Access Edge Computing (MEC) nodes, integrates a novel demand response (DR) strategy to manage real-time power use effectively. Synthetic data tests achieved a 100% acceptance rate with zero reliance on non-renewable power, while real-world tests reduced non-renewable power consumption by over 90%, demonstrating the system’s flexibility. These results provide a foundation for further AI-based heuristics optimization techniques to improve scalability and power efficiency in broader smart city deployments., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Modeling and performance evaluation for electromagnetic micro/nano-gateway

  • Galal Mahmoud Ibrahim, Akram|||0000-0002-3852-7436
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
The Internet of nano-things communication has increased attention in recent years, serving different applications in many fields. Such applications need uplink and downlink communication between the nano-network and the macro-domain world through macro/nano-interfaces, where nano-sensors/actuators communicate with smart hybrid devices called micro/nano-gateways. The analytical evaluation of such gateways is mandatory, as it requires a precise study of their performance in handling traffic in the upstream/downstream directions. In this paper, an analytical evaluation of the micro/nano-gateway performance is studied using queueing theory to describe the behavior of the gateway handling the nano-network upstream traffic. The analytical investigation illustrates how different classes of upstream traffic will be processed by the gateway and distributed over three different queues according to traffic characteristics. The study shows the effect of the number of running servers inside each queue and the buffer size on the overall performance of the micro/nano-gateway., This work has been supported by the “Agencia Estatal de Investigación” of “Ministerio de Ciencia e Innovación” of Spain under project 6G-INSPIRE PID2022-137329OB-C41/ MCIN/ AEI/10.13039/ 501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

An experimental tethered UAV-based communication system with continuous power supply

  • Rodríguez Ortega, Verónica
  • Tipantuña Tenelema, Christian José
  • Reinoso Chisaguano, Diego Javier
  • Carvajal Rodríguez, Jorge
  • Egas Acosta, Carlos
  • Proaño Chamorro, Pablo Andrés
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
Ensuring reliable communication in remote or disaster-affected areas is a technical challenge due to unplanned deployment and mobilization, meaning placement difficulties and high operation costs of conventional telecommunications infrastructures. To address this problem, unmanned aerial vehicles (UAVs) have emerged as an excellent alternative to provide quick connectivity in remote or disaster-affected regions at a reasonable cost. However, the limited battery autonomy of UAVs restricts their flight service time. This paper proposes a communication system based on a tethered UAV (T-UAV) capable of continuous operation through a wired power network connected to a ground station. The communications system is based on low-cost devices, such as Raspberry Pi platforms, and offers wireless IP telephony services, providing high-quality and reliable communication. Experimental tests assessed power consumption, UAV stability, and data transmission performance. Our results prove that the T-UAV, based on a quadcopter drone, operates stably at 16 V and 20 A, ensuring consistent VoIP communications at a height of 10 m with low latency. These experimental findings underscore the potential of T-UAVs as cost-effective alternatives for extending or providing communication networks in remote regions, emergency scenarios, or underserved areas., This work is part of the I+D+i project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER, UE. Escuela Politécnica Nacional supported this work through the project PIIF-24-06., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A simulator for testing and developing scheduling mechanisms in integrated 5G/6G-TSN scenarios

  • Agustí Torra, Anna|||0000-0002-2551-5698
  • Sierra Guerrero, Cilia Ines
  • Jofre Cruanyes, Marc|||0000-0002-8912-6595
  • Rincón Rivera, David|||0000-0003-1294-3842
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Time-Sensitive Networking (TSN) is an Ethernetbased technology that provides Quality-of-Service (QoS) guarantees, making it ideal for industrial communications. The 3GPP has designed scenarios where 5G (and future 6G) networks integrate with TSN in industrial deployments, adding mobility and flexibility to wire-based TSN networks. In this context, TSN scheduling mechanisms play an important role. This paper presents a simulator developed to test scheduling mechanisms for TSN controllers. The basic operation of the simulator is presented. Finally, preliminary results obtained using the two scheduling mechanisms currently implemented are described., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union—NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15–6GSMARTEZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under I+D+i project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER (EU)
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Digital Twin Networks requirements: towards an ultra-reliable infrastructure

  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
  • Calle Heredia, Xavier Ezequiel
Digital Twin Networks (DTNs) enable a new generation of applications, ranging from medical, social and spatial communications. The deployment demands ultra-reliable, high-speed, and latency-aware network infrastructure to provide synchronization and integrity, requiring massive data transmission. As DTNs scales, challenges such as bandwidth constraints, latency and network reliability become critical. This paper explores the evolving network requirements of DTNs, highlighting key challenges and potential solutions for several scenarios. Addressing these demands is essential for ensuring seamless DTN operations., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Federated learning system for dynamic Radio/MEC resource allocation and slicing control in open radio access network

  • Martínez Morfa, Mario José|||0009-0009-9130-1493
  • Ruiz de Mendoza, Carlos Ausias|||0000-0002-1262-9952
  • Cervelló Pastor, Cristina|||0000-0002-8056-0774
  • Sallent Ribes, Sebastián|||0000-0002-8232-6180
The evolution of cellular networks from fifth-generation (5G) architectures to beyond 5G (B5G) and sixth-generation (6G) systems necessitates innovative solutions to overcome the limitations of traditional Radio Access Network (RAN) infrastructures. Existing monolithic and proprietary RAN components restrict adaptability, interoperability, and optimal resource utilization, posing challenges in meeting the stringent requirements of next-generation applications. The Open Radio Access Network (O-RAN) and Multi-Access Edge Computing (MEC) have emerged as transformative paradigms, enabling disaggregation, virtualization, and real-time adaptability—which are key to achieving ultra-low latency, enhanced bandwidth efficiency, and intelligent resource management in future cellular systems. This paper presents a Federated Deep Reinforcement Learning (FDRL) framework for dynamic radio and edge computing resource allocation and slicing management in O-RAN environments. An Integer Linear Programming (ILP) model has also been developed, resulting in the proposed FDRL solution drastically reducing the system response time. On the other hand, unlike centralized Reinforcement Learning (RL) approaches, the proposed FDRL solution leverages Federated Learning (FL) to optimize performance while preserving data privacy and reducing communication overhead. Comparative evaluations against centralized models demonstrate that the federated approach improves learning efficiency and reduces bandwidth consumption. The system has been rigorously tested across multiple scenarios, including multi-client O-RAN environments and loss-of-synchronization conditions, confirming its resilience in distributed deployments. Additionally, a case study simulating realistic traffic profiles validates the proposed framework’s ability to dynamically manage radio and computational resources, ensuring efficient and adaptive O-RAN slicing for diverse and high-mobility scenarios.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

AI-driven sub-6 GHz SDR-based and low-cost spectrum analyzer for 5G and 6G networks

  • Suárez, Tiffany|||0009-0008-4850-7317
  • Tipantuña Tenelema, Christian José
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
  • Vinueza Bustamante, Marco|||0009-0000-3946-3334
  • Cevallos Brusil, Danilo Gabriel|||0009-0002-9520-7831
  • Yépez Vera, Carlos|||0009-0005-7321-4637
A spectrum analyzer is an essential instrument in telecommunications for observing and analyzing the power distribution of a signal across different frequencies. Traditionally, these devices are expensive and complex, limiting their accessibility. This paper presents an affordable spectrum analyzer prototype using a software-defined radio (SDR) module and a Raspberry Pi, coupled with a 10.1-inch touchscreen. Based on the HackRF One and Raspberry Pi 4B+, the system uses GNU Radio to capture, analyze, and display electromagnetic-signal spectra from 1 MHz to 6 GHz. The user-friendly interface and artificial intelligence-based voice module enable easy, accessible real-time selection of frequencies, bandwidth adjustment, and signal visualization, applicable to 5G and 6G networks., Escuela Politécnica Nacional supported this work. Furthermore, this work is part of the I+D+i project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Building a 5G-TSN testbed: architecture and challenges

  • Agustí Torra, Anna|||0000-0002-2551-5698
  • Ferré Mancebo, Marc
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Cervelló Pastor, Cristina|||0000-0002-8056-0774
  • Sallent Ribes, Sebastián|||0000-0002-8232-6180
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Time-Sensitive Networking (TSN) is one of the best networking technologies currently available for industrial communications, due to its strict Quality-of-Service (QoS) guarantees. TSN defines several mechanisms, where packet schedulers play the most important role. The Time-Aware Shaper (TAS) is the scheduler best suited for industrial scenarios, since it is able to assign periodic timeslots to specific flows, thus ensuring QoS if routing and scheduling are correctly configured by the Software-Defined Networking (SDN)-based TSN control plane. However, TSN is a wire-based technology that lacks the flexibility and mobility provided by wireless technologies such as 5G. This is why 3GPP, starting from Release 16, has defined an architecture for the integration of (typically private) 5G networks and TSN in industrial scenarios. New elements, called TSN Translators (TTs), are needed between the 5G and TSN data planes, and an interface, named TSN Application Function (AF), is defined in 5G to communicate the control planes of both networks. This paper describes the architecture, challenges, and preliminary results obtained from a 5G-TSN network testbed (including TSN equipment and 5G emulators, and an SDN-based control plane)., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union - NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15– 6GSMART-EZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/50110001103, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura::9.4 - Per a 2030, modernitzar les infraestructures i reconvertir les indústries perquè siguin sostenibles, usant els recursos amb més eficàcia i promovent l’adopció de tecnologies i processos industrials nets i racionals ambiental­ment, i aconseguint que tots els països adoptin mesures d’acord amb les capacitats respectives
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Precision time protocol synchronization analysis for single and coincidence qubit detection in quantum networks

  • Jofre Cruanyes, Marc|||0000-0002-8912-6595
  • Saigi, Ferran
  • Rincón Rivera, David|||0000-0003-1294-3842
2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The combination of Quantum and Telecommunications networks, offering unparalleled quantum correlation-based capabilities and making it an ideal choice for certain critical applications, requires precise time synchronization across network nodes. This work analytically and experimentally assessed the application of the IEEE 1588 Precision Time Protocol in achieving time synchronization within quantum networks. As results, operating at a repetition rate of 5MHz, the overall time synchronization precision is 65ns for single-qubit detection and 100ns for double-fold coincidence measurements. Correspondingly, the experimental results highlight the role of time-synchronization precision protocols in multi-node quantum networks and also provide insights for further developments for scalable quantum network infrastructure., This work was financially supported by PID2022-137329OB-C41 and PID2022-136869NB-C31 (MCIN / AEI / 10.13039 / 501100011033 / FEDER, UE), CNS2024-154600, PDC2022-133091-I00, grants of the Agencia Estatal de Investigaci´ on (Spain), Catalan Government University and Research Aid Management Agency (AGAUR) with Research Group grant 2021 SGR 01046, and ALECTORS 2024 grant from Universitat Polit` ecnica de Catalunya- BarcelonaTech (UPC).
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Proposal of architecture for extended reality network functions in Digital Twin Networks

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
The emergence of Extended Reality (XR) has provided the path towards the deployment of novel networking applications that enhances both the way users interact in digital environments and the network experience. On the other hand, Digital Twin Networks (DTNs) are envisioned as a promising paradigm to revolutionize the conventional lifecycle management of networks by means of realtime simulations, network prediction, resilience, orchestration, among others. The integration of previously mentioned technologies enable the deployment of novel and immersive network functions operating within a Digital Twin Network environment; the proposed synergy is envisioned to offer promising solutions to be exploited in multiple use cases including: networking, telemedicine, space exploration, and autonomous driving. To support this integration, an architecture must be provided with the aim of offering a robust infrastructure able to cover cost demands for XR services while offloading processing capabilities from client devices such as smartphones, laptops, IoT devices, etc., This work is part of the I+D+i project PID2022-137329OB-C41, supported by MI-CIU/AEI/10.13039/501100011033 and FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Multi-agent reinforcement learning-based routing and scheduling models in time-sensitive networking for internet of vehicles communications between transportation field cabinets

  • Garcia Cantón, Sergi|||0000-0002-6051-1406
  • Ruiz de Mendoza, Carlos Ausias|||0000-0002-1262-9952
  • Cervelló Pastor, Cristina|||0000-0002-8056-0774
  • Sallent Ribes, Sebastián|||0000-0002-8232-6180
Future autonomous vehicles will interact with traffic infrastructure through roadside units (RSUs) directly connected to transportation field cabinets (TFCs). These TFCs must be interconnected to share traffic information, enabling infrastructure-to-infrastructure (I2I) communications that are reliable, synchronous and capable of transmitting vehicle data to the Internet. However, I2I communications present a complex optimization challenge. This study addresses this by proposing the design, implementation, and evaluation of an automated management model for I2I service channels based on multi-agent reinforcement learning (MARL) integrated with deep reinforcement learning (DRL). The proposed models efficiently manage the routing and scheduling of data frames between internet of vehicles (IoV) infrastructure devices through time-sensitive networking (TSN) to ensure real-time synchronous I2I communications. The solution incorporates both a routing model and a scheduling model, evaluated in a simulated shared environment where agents operate within the TSN control plane. Both models are tested for different topologies and background traffic levels. The results demonstrate that the models establish the majority of paths in the scenario, adhering to near-optimal routing and scheduling policies. Recursively, for each individual request to create a service channel, the system establishes online an optimal synchronous path between entities with a limited time budget. In total, 71% of optimal routing paths are established and 97% of optimal schedules are achieved. The approach takes into account the periodic nature of the transmitted data and its robustness through TSN networks, obtaining 99 percent of compliant service requests with flow jitter levels below 100 microseconds for different topologies and different network utility percentages. The proposed solution achieves lower execution delays compared to the iterative ILP approach. Additionally, the solution facilitates the integration of 5G networks for vehicle-to-infrastructure (V2I) communications, which is identified as an area for future exploration., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union—NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15–6GSMART-EZ), as well as by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/50110001103.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A microservices-based control plane for time-sensitive networking

  • Agustí Torra, Anna|||0000-0002-2551-5698
  • Ferré Mancebo, Marc
  • Orozco Urrutia, Gabriel David
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Remondo Bueno, David|||0000-0002-7461-1766
Time-Sensitive Networking (TSN) aims to provide deterministic communications over Ethernet. The main characteristics of TSN are bounded latency and very high reliability, thus complying with the strict requirements of industrial communications or automotive applications, to name a couple of examples. In order to achieve this goal, TSN defines several scheduling algorithms, among them the Time-Aware Shaper (TAS), which is based on time slots and Gate Control Lists (GCLs). The configuration of network elements to allocate time slots, paths, and GCLs is laborious, and has to be updated promptly and in a dynamic way, as new data flows arrive or disappear. The IEEE 802.1Qcc standard provides the basis to design a TSN control plane to face these challenges, following the Software-Defined Networking (SDN) paradigm. However, most of the current SDN/TSN control plane solutions are monolithic applications designed to run on dedicated servers, and do not provide the required flexibility to escalate when facing increasing service requests. This work presents 𝜇 TSN-CP, an SDN/TSN microservices-based control plane, based on the 802.1Qcc standard. Our architecture leverages the advantages of microservices, enabling the control plane to scale up or down in response to varying workloads dynamically. We achieve enhanced flexibility and resilience by breaking down the control plane into smaller, independent microservices. The performance of 𝜇 TSN-CP is evaluated in a real environment with TSN switches, and various integer linear problem solvers, running over different computing platforms.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Multimodal and Social Virtual Reality (VR): exploring and validating promising enablers for next-generation interactive and group-based virtual visits

  • Hjeij, Mohamad Kassem
  • Montagud Climent, Mario
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Fernández Langa, Sergi
Social Virtual Reality (VR) is emerging as a powerful medium for remote social interaction and collaboration, enabling multiple users to share experiences together while apart. Likewise, recent advances in multimedia technologies have proposed strategically combining diverse content formats and introducing interaction techniques for recreating virtual environments and engaging with them, respectively. This study pioneers the joint exploration of Social VR enhanced with holographic communication, multimodal content integration, and advanced interaction methods to deliver realistic and interactive group visits to reconstructed cultural heritage sites, specifically an existing restaurant–museum. The reconstructed space is further augmented with Points of Interest (PoIs), which can be freely visited and dynamically activated to provide rich contextual and historical information about the venue. The proposed technology and scenario have been evaluated objectively and subjectively. Results from objective tests offer relevant insights into the technical requirements, performance metrics (including bandwidth usage and latency), and overall system stability. Results from subjective tests with 22 participant pairs reveal high levels of user satisfaction, particularly in terms of immersion, presence, togetherness, and interaction quality regardless of whether participants acted as Guides (interacting with the VR environment) or Followers (observing and following the Guide’s actions). Beyond demonstrating feasibility, the findings from this study prove, for the first time, how strategically combining multi-user holoportation with multimodal content and role-based interactions can enable guided, collaborative cultural or touristic visits that preserve social presence while supporting rich exploration and contextual learning., This work has been funded by the European Union’s Horizon Europe program, under agreement n° 101135025 (PRESENCE project), and by Agencia Estatal de Investigación (AEI), in the framework of Proyectos Generación de Conocimiento 2022, under agreement PID2022-140749OBI0 (EVOLVE project). The work of Mohamad Hjeij has been funded by the Generalitat de Catalunya and the European Social Fund (Juan Oro Grants to hire research staff in training FI 2022). The work of Mario Montagud has been funded by MCIN/AEI/10.13039/501100011033 under Grant RYC2020-030679-I and by “the European Social Fund (ESF) Investing in Your Future”. The work of David Rincón Rivera has been funded by project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER, EU., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

LQ-GNN: a Graph Neural Network model for response time prediction of microservice-based applications in the computing continuum

  • Richart Gutiérrez, Matías Mario|||0000-0002-9152-3522
  • Gorricho Moreno, Juan Luis|||0000-0002-6280-1546
  • Baliosian De Lazzari, Javier Ernesto
  • Contreras, Luis Miguel
  • Muñiz, Alejandro
  • Serrat Fernández, Juan|||0000-0002-4551-9880
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., To address the challenges posed by the deployment of microservices of future end-user applications in the cloud continuum, a performance prediction model working together with a network elasticity controller will be needed. With that aim, this work introduces Layered Queuing-Graph Neural Networks (LQ-GNN), a novel Machine Learning (ML) approach to develop a generalized performance prediction model for microservice-based applications. Unlike previous works focused on individual applications, our proposal aims for a versatile model applicable to any microservice-based application, integrating the Layered Queueing Network (LQN) modeling with Graph Neural Networks (GNN). LQ-GNN allows to efficiently estimate the response time of applications under different resource allocations and placements on the computing continuum. The obtained evaluation results indicate that the proposed model achieves a prediction error below 10% when considering different evaluation scenarios. Compared to existing methodologies, our approach balances prediction accuracy and computational efficiency, making it viable for real-time deployments. Consequently, ML-based performance prediction can significantly enhance the resource management and elasticity control of microservice-based architectures, leading to more resilient and efficient systems., This work has been partially funded by the project “UNICO-5G I+D-OPTIMAIX-TSI-063000-2021-34”, by the Beatriu de Pin´ os Programme of the Ministry of Research and Universities of the Government of Catalonia under grant 2022-BP-00099 and also supported by the Agencia Estatal de Investigaci´ on of Ministerio de Ciencia e Innovaci´ on of Spain under project PID2022-137329OB-C41 /MCIN/AEI/10.13039/501100011033.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Digital twin-driven virtual network architecture for enhanced extended reality capabilities

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
Extended Reality (XR) technology is proposed as a key enabler for the development of immersive applications, thus transforming the way users interact within digital environments. In communication networks, XR will be able to introduce immersive network functions with the potential to enhance the network experience. This paper proposes a comprehensive architectural framework designed to support the deployment of XR Functions (XRFs) within a Digital Twin Network (DTN) environment in order to provide immersive functions of any type, including control and management functions, that are not available in the original network. The proposal can be deployed in relevant fields where digital twins are promising, such as medical applications, surveillance systems, autonomous driving and space communications. The proposed architecture must consider the need for minimal hardware and software resources, along with a network topological configuration with the objective of providing a robust yet lightweight framework, allowing devices with limited computing power, such as smartphones and laptops, to benefit from the enhanced network functionalities provided in the Digital Twin Network, without affecting the original network (ON)., This workhasbeensupportedbytheAgenciaEstataldeInvestigación ofMinisterio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

An intent conflict detection and resolution model for transport connectivity services

  • Alemany, Pol
  • Niknahad, Hadi
  • Adanza, Daniel
  • Díaz Rivera, Javier José
  • Gifré Renom, Lluis
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Vilalta, Ricard
  • Muñoz, Raul
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper presents a solution for detecting and resolving conflicts in Intent-Based Networking (IBN) for transport connectivity services. As networks become more complex, IBN allows high-level, goal-oriented management, but conflicts between overlapping intents can degrade performance or security. The paper proposes a two-level conflict detection model—within a single intent (intra-intent) and between multiple intents (inter-intent)—focusing on key service quality attributes like latency, bandwidth, and packet loss. A resolution model combines priority-based allocation and weighted fair sharing to ensure fair resource distribution. The solution was validated using the ETSI TeraFlow SDN controller, showing fast conflict detection and resolution, typically within milliseconds. The results confirm its effectiveness for real-time network management in dynamic environments like IoT and 5G, 6G and beyond., This work is partially funded by the EC through the ACROSS (101097122) project, partially by the Ministerio de Asuntos Económicos y Transformación Digital and the European Union-Next GenerationEU in the frameworks of the Plan de Recuperación, Transformación y Resiliencia and of the Mecanismo de Recuperación y Resiliencia through UNICO-5G I+D 6GMICROSDN project under references TSI-063000-2021-19, TSI-063000-2021-20, TSI063000-2021-21, and the MCIN/AEI/10.13039/501100011033/FEDER/UE, and by the RELAMPAGO project (Grant PID2021-127916OB-I00) funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU, and by the project 6G-INSPIRE PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER (EU).
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Deep reinforcement learning-based joint scheduling and routing for Time-Sensitive Networks

  • Garcia Cantón, Sergi|||0000-0002-6051-1406
  • Cervelló Pastor, Cristina|||0000-0002-8056-0774
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Sallent Ribes, Sebastián|||0000-0002-8232-6180
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., In the deployment of 5G and the development of the future 6G, a set of use cases are generated that require URLLC (Ultra-Reliable Low Latency communications) service-type communications with very low latency and extremely high reliability. At the same time, verticals such as Industry 4.0 require Key Performance Indicators (KPIs) that can only be offered by deterministic networks. Time Sensitive Networking (TSN) is a set of IEEE 802.1 standards that aim to provide highly reliable, low-latency deterministic communications over Ethernet. The IEEE 802.1Qcc standard defines three architectural models for TSN networks. One of them is fully centralized, which is based on an SDN architecture where the control plane is distributed between two entities: the Centralized Network Configuration (CNC) and the Centralized User Configuration (CUC). These systems' increasing complexity and scalability led to the introduction of Machine Learning (ML) tools that will allow them to move towards zero-touch. Currently, solutions are proposed using Integer Linear Programming (ILP), whose computational complexity implies a significant lack of scalability, which worsens as the network size or traffic heterogeneity increases. This paper describes a traffic scheduling and routing algorithm based on deep reinforcement learning (DRL), which is located in the CNC, receiving requests from CUC users and configuring and maintaining the Gate Control lists of the Ethernet switches. The proposed mechanism jointly solves a deterministic routing of data flows with scheduling. This proposal also optimizes the load balancing of the links and the occupation of the time slots of each link., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union— NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15– 6GSMART-EZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/50110001103., Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura::9.4 - Per a 2030, modernitzar les infraestructures i reconvertir les indústries perquè siguin sostenibles, usant els recursos amb més eficàcia i promovent l’adopció de tecnologies i processos industrials nets i racionals ambiental­ment, i aconseguint que tots els països adoptin mesures d’acord amb les capacitats respectives
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Qubit rate modulation-based time synchronization mechanism for multi-node quantum networks

  • Jofre Cruanyes, Marc|||0000-0002-8912-6595
The combination of quantum and telecommunication networks enables to revolutionize the way information is used, offering unparalleled capabilities and making it an ideal choice for many critical applications. In this sense, quantum protocols generally have a unique requirement to have strict time synchronization in order to operate, which generally consume quantum resources of part of the exchanged qubits. Accordingly, work demonstrates and characterizes a temporal alignment mechanism for quantum networks based on frequency testing, allowing to preserve the quantum state of qubits. The time synchronization correction achieved is within 100 ns working at 5 MHz with temporal and relative frequency offsets commonly acquired in quantum links using conventional hardware clocks with temporal stability in the range of 10-8 and 200-ns jitter., This work was supported in part by the Agencia Estatal de Investigación (Spain) under Grant PID2022-137329OB-C41, Grant PID2022-136869NB-C31 (MCIN/AEI/10.13039/501100011033/FEDER, UE), Grant CNS2024-154600, and Grant PDC2022-133091-I00, in part by the Catalan Government University and Research Aid Management Agency (AGAUR) with Research Group under Grant 2021 SGR 01046, and in part by the Technical University of Catalonia (UPC) under Grant ALECTORS 2024.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Performance evaluation methodology for federated XR network digital twins in AI-aware 6G networks

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
Network digital twins (NDTs) are emerging as key enablers of 6G networks integrating artificial Intelligence (AI) techniques. NDT systems offer novel features, including real-time monitoring, simulation, enhanced network planning, autonomous management, seamless integration with emerging technologies such as extended reality (XR), among others. When NDTs converge with XR, NDTs can be customized with additional interactive services that are not available in the original network. In this work, artificial intelligence (AI) strategies are applied to a set of XR functions within federated NDTs. While existing NDT approaches follow a one-to-one (1:1) model, where a single NDT instance is deployed from an original network, the one-to-many (1:N) federation model requires the orchestration of multiple XR-tailored NDT instances. The federation of NDTs can be applied across diverse 6G use cases, including telemedicine, UAV management, Industry 4.0, and the remote driving of complex vehicles. Ensuring the optimal operation of the NDT federation requires a methodology tailored to the requirements of each use case. This paper introduces a score-based performance analysis to quantify the benefits achieved through NDT federation. Unlike existing models for the digital twin (DT) federation, this paper introduces a KPI-based rational model that quantifies the trade-off between federation benefits and the associated operational complexity. A mathematical analysis is performed to validate the consistency of the score formula both in general terms and within the context of each specific use case., This work is part of the I+D+i project PID2022-137329OB-C41 and supported by MICIU/AEI/10.13039/501100011033 and FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

SDN-enabled digital twin networks architecture for proactive detection and mitigation of malicious encrypted traffic

  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
  • Parada Claro, Juan
Classification algorithms for encrypted traffic are an effective means of improving the security of private networks. However, they operate a posteriori because they require collecting flow level features (packet length, inter-arrival time, and flow identifiers), which can only be extracted after observing multiple packets before reaching a classification decision. Furthermore, to achieve accurate classification, the analyzed flows must be processed by the target server or by a server that faithfully replicates its behavior. This paper proposes a Digital Twin Network (DTN) architecture to prevent unknown traffic from being initially processed by the Original Network, thereby reducing the risk of attacks that cannot be immediately detected by encrypted traffic classification. The architecture integrates SDN and P4 to implement the monitoring and traffic redirection required by the DTN, and a proof-of-concept prototype is presented to validate its functionality. This work identifies a trade-off regarding access to previously unknown external services due to redirection via the DTN until classification is complete, which can introduce significant delays.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Reinforcement learning and multi-access edge computing for 6G-Based underwater wireless networks

  • Cepeda Pacheco, Juan Carlos
  • Domingo Aladrén, Mari Carmen|||0000-0002-6901-3817
6G networks are envisioned to dramatically enhance the connectivity landscape by integrating communication across ground, air, and sea environments. In the aquatic domain, the Internet of Underwater Things (IoUT) represents a global network of intelligent underwater devices designed to capture, interpret, and share data. Although Underwater Acoustic Communications (UAC) has become widespread as a solution for transmitting information, data collection from Underwater Sensor Nodes (USNs) to the surface results in extensive delays and higher energy consumption. Edge communication emerges as a solution to address these challenges. In this approach, Autonomous Underwater Vehicles (AUVs) bring edge computing as close as possible to the source devices. This paper proposes an innovative AUV-based Multi-Access Edge Computing (MEC) system where cluster-heads that collect data from IoUT devices offload their associated computational tasks to local AUVs. These AUVs are strategically positioned to execute tasks either fully locally, partially, or by offloading them entirely to a more resource-equipped AUV (AUV MEC). We achieve this by jointly optimizing the task offloading strategy, resource allocation, and the trajectories of the AUVs. We formulate a non-convex optimization problem to minimize the weighted sum of service delays for all local AUVs and their energy consumption. To address the NP-hard nature of this problem, we employ a deep reinforcement learning algorithm, Deep Deterministic Policy Gradient (DDPG), to solve it. Extensive simulations have been conducted to evaluate the effectiveness of our proposed communication system. The results show that our proposed algorithm outperforms the Total Offloading (Offloading), Local Execution (Locally), and Actor-Critic (AC) algorithms.
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Aproximación hacia arquitecturas modulares asistidas por computación en el borde para optimización de comunicaciones holográficas

  • Castillo Gómez-Raya, Genís
  • Fernández Langa, Sergi
  • Rincón Rivera, David|||0000-0003-1294-3842
  • Montagud Climent, Mario
Este artículo presenta una aproximación inicial hacia arquitecturas modulares asistidas por computación en el borde (Edge Computing) orientadas a una optimización de la prestación de servicios de comunicaciones holográficas multiusuario. Se propone una modularización de componentes y módulos en el lado servidor que, por una parte, permite desacoplar el plano de control del plano de datos de usuario y, por otra parte, facilita una gestión dinámica de conexiones en función de requerimientos específicos y a los recursos disponibles. La arquitectura propuesta, junto con sus mecanismos de orquestación asociados, se adapta y reconfigura mediante la especificación e integración de APIs de red compatibles con iniciativas de estandarización actuales. Los beneficios de esta aproximación se validan preliminarmente a través de pruebas experimentales que evidencian, por un lado, las ventajas de utilizar servidores de borde para la gestión de comunicaciones, y por otro, el impacto positivo del balanceo de carga entre componentes servidor en cuanto a la escalabilidad y estabilidad del servicio., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A novel architecture for virtual network twin deployment

  • Banisadr, Amir Hossein
  • Hesselbach Serra, Xavier|||0000-0002-7888-3603
In this paper, a novel architecture is proposed that enhances network connectivity by combining network virtualization and the digital twin approach. A virtual network twin (VNT) framework is designed to emulate the behavior of the original network within a virtualized environment. This framework provides an enhanced connection experience for users, mirroring the performance of the original network while avoiding the limitations of previous methods such as Telnet, SSH, and VPN. By integrating the network virtualization approach and the concept of digital twins, this framework can improve network visibility, security, and robustness in real-time connectivity through appropriate communication protocols and artificial intelligence (AI) methods. The application of this proposal can significantly impact key areas such as medical applications, autonomous driving, and space communications. This paper introduces the VNT architecture; its core components; requirements; and evaluation metrics, such as the accuracy of the VNT., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Optimized provisioning technique of future services with different QoS requirements in multi-access edge computing

  • Ssemakula, John Bosco
  • Gorricho Moreno, Juan Luis
  • Kibalya, Godfrey Mirondo
  • Serrat Fernández, Juan
With the present trend towards the use of microservices instead of monolithic software, future applications with diverse computational and delay-sensitive requirements, such as virtual reality (VR) or holographic communications (HC), will be redesigned based on loosely coupled microservices due to their more efficient deployment according to available resources. However, it remains a big challenge to provide such services under stringent quality of service (QoS) requirements at minimum time and cost and with an efficient utilization of the network. Presently, multi-access edge computing (MEC) has been proposed as a promising alternative to deploy future microservice-based applications to achieve faster response times while reducing the overall network load. However, network conditions, edge nodes state and service requests are dynamic, increasing the difficulty for the provisioning of services by MECs. In this context, we propose an optimization deployment heuristic (ODA) to obtain sub-optimal deployments in reasonable time, meeting the requirements of some representative future applications under study. In particular, according to latency requirements, there will be delay-tolerant and delay-sensitive applications, playing a major role regarding the alternatives for the deployment onto single or multiple MEC systems. The evaluation analysis shows that our proposal performs significantly better than other benchmark solutions in most of the metrics used for the experiments, especially in minimizing deployment costs in minimal time., Preprint
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Modeling and performance evaluation for electromagnetic micro/nano-gateway

  • Galal Mahmoud Ibrahim, Akram
  • Hesselbach Serra, Xavier
The Internet of nano-things communication has increased attention in recent years, serving different applications in many fields. Such applications need uplink and downlink communication between the nano-network and the macro-domain world through macro/nano-interfaces, where nano-sensors/actuators communicate with smart hybrid devices called micro/nano-gateways. The analytical evaluation of such gateways is mandatory, as it requires a precise study of their performance in handling traffic in the upstream/downstream directions. In this paper, an analytical evaluation of the micro/nano-gateway performance is studied using queueing theory to describe the behavior of the gateway handling the nano-network upstream traffic. The analytical investigation illustrates how different classes of upstream traffic will be processed by the gateway and distributed over three different queues according to traffic characteristics. The study shows the effect of the number of running servers inside each queue and the buffer size on the overall performance of the micro/nano-gateway., This work has been supported by the “Agencia Estatal de Investigación” of “Ministerio de Ciencia e Innovación” of Spain under project 6G-INSPIRE PID2022-137329OB-C41/ MCIN/ AEI/10.13039/ 501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Cost-effective power management for smart homes: innovative scheduling techniques and integrating battery optimization in 6G networks

  • Riad Al-taie, Rana
  • Hesselbach Serra, Xavier
This paper presents an Optimal Power Management System (OPMS) for smart homes in 6G environments, which are designed to enhance the sustainability of Green Internet of Everything (GIoT) applications. The system employs a brute-force search using an exact solution to identify the optimal decision for adapting power consumption to renewable power availability. Key techniques, including priority-based allocation, time-shifting, quality degradation, battery utilization and service rejection, will be adopted. Given the NP-hard nature of this problem, the brute-force approach is feasible for smaller scenarios but sets the stage for future heuristic methods in large-scale applications like smart cities. The OPMS, deployed on Multi-Access Edge Computing (MEC) nodes, integrates a novel demand response (DR) strategy to manage real-time power use effectively. Synthetic data tests achieved a 100% acceptance rate with zero reliance on non-renewable power, while real-world tests reduced non-renewable power consumption by over 90%, demonstrating the system’s flexibility. These results provide a foundation for further AI-based heuristics optimization techniques to improve scalability and power efficiency in broader smart city deployments., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Federated learning system for dynamic Radio/MEC resource allocation and slicing control in open radio access network

  • Martínez Morfa, Mario José
  • Ruiz de Mendoza, Carlos Ausias
  • Cervelló Pastor, Cristina
  • Sallent Ribes, Sebastián
The evolution of cellular networks from fifth-generation (5G) architectures to beyond 5G (B5G) and sixth-generation (6G) systems necessitates innovative solutions to overcome the limitations of traditional Radio Access Network (RAN) infrastructures. Existing monolithic and proprietary RAN components restrict adaptability, interoperability, and optimal resource utilization, posing challenges in meeting the stringent requirements of next-generation applications. The Open Radio Access Network (O-RAN) and Multi-Access Edge Computing (MEC) have emerged as transformative paradigms, enabling disaggregation, virtualization, and real-time adaptability—which are key to achieving ultra-low latency, enhanced bandwidth efficiency, and intelligent resource management in future cellular systems. This paper presents a Federated Deep Reinforcement Learning (FDRL) framework for dynamic radio and edge computing resource allocation and slicing management in O-RAN environments. An Integer Linear Programming (ILP) model has also been developed, resulting in the proposed FDRL solution drastically reducing the system response time. On the other hand, unlike centralized Reinforcement Learning (RL) approaches, the proposed FDRL solution leverages Federated Learning (FL) to optimize performance while preserving data privacy and reducing communication overhead. Comparative evaluations against centralized models demonstrate that the federated approach improves learning efficiency and reduces bandwidth consumption. The system has been rigorously tested across multiple scenarios, including multi-client O-RAN environments and loss-of-synchronization conditions, confirming its resilience in distributed deployments. Additionally, a case study simulating realistic traffic profiles validates the proposed framework’s ability to dynamically manage radio and computational resources, ensuring efficient and adaptive O-RAN slicing for diverse and high-mobility scenarios., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Proposal of architecture for extended reality network functions in Digital Twin Networks

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier
The emergence of Extended Reality (XR) has provided the path towards the deployment of novel networking applications that enhances both the way users interact in digital environments and the network experience. On the other hand, Digital Twin Networks (DTNs) are envisioned as a promising paradigm to revolutionize the conventional lifecycle management of networks by means of realtime simulations, network prediction, resilience, orchestration, among others. The integration of previously mentioned technologies enable the deployment of novel and immersive network functions operating within a Digital Twin Network environment; the proposed synergy is envisioned to offer promising solutions to be exploited in multiple use cases including: networking, telemedicine, space exploration, and autonomous driving. To support this integration, an architecture must be provided with the aim of offering a robust infrastructure able to cover cost demands for XR services while offloading processing capabilities from client devices such as smartphones, laptops, IoT devices, etc., This work is part of the I+D+i project PID2022-137329OB-C41, supported by MI-CIU/AEI/10.13039/501100011033 and FEDER, UE., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

LQ-GNN: a Graph Neural Network model for response time prediction of microservice-based applications in the computing continuum

  • Richart Gutiérrez, Matías Mario
  • Gorricho Moreno, Juan Luis
  • Baliosian De Lazzari, Javier Ernesto
  • Contreras, Luis Miguel
  • Muñiz, Alejandro
  • Serrat Fernández, Juan
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., To address the challenges posed by the deployment of microservices of future end-user applications in the cloud continuum, a performance prediction model working together with a network elasticity controller will be needed. With that aim, this work introduces Layered Queuing-Graph Neural Networks (LQ-GNN), a novel Machine Learning (ML) approach to develop a generalized performance prediction model for microservice-based applications. Unlike previous works focused on individual applications, our proposal aims for a versatile model applicable to any microservice-based application, integrating the Layered Queueing Network (LQN) modeling with Graph Neural Networks (GNN). LQ-GNN allows to efficiently estimate the response time of applications under different resource allocations and placements on the computing continuum. The obtained evaluation results indicate that the proposed model achieves a prediction error below 10% when considering different evaluation scenarios. Compared to existing methodologies, our approach balances prediction accuracy and computational efficiency, making it viable for real-time deployments. Consequently, ML-based performance prediction can significantly enhance the resource management and elasticity control of microservice-based architectures, leading to more resilient and efficient systems., This work has been partially funded by the project “UNICO-5G I+D-OPTIMAIX-TSI-063000-2021-34”, by the Beatriu de Pin´ os Programme of the Ministry of Research and Universities of the Government of Catalonia under grant 2022-BP-00099 and also supported by the Agencia Estatal de Investigaci´ on of Ministerio de Ciencia e Innovaci´ on of Spain under project PID2022-137329OB-C41 /MCIN/AEI/10.13039/501100011033., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

SDN-enabled digital twin networks architecture for proactive detection and mitigation of malicious encrypted traffic

  • Hesselbach Serra, Xavier
  • Parada Claro, Juan
Classification algorithms for encrypted traffic are an effective means of improving the security of private networks. However, they operate a posteriori because they require collecting flow level features (packet length, inter-arrival time, and flow identifiers), which can only be extracted after observing multiple packets before reaching a classification decision. Furthermore, to achieve accurate classification, the analyzed flows must be processed by the target server or by a server that faithfully replicates its behavior. This paper proposes a Digital Twin Network (DTN) architecture to prevent unknown traffic from being initially processed by the Original Network, thereby reducing the risk of attacks that cannot be immediately detected by encrypted traffic classification. The architecture integrates SDN and P4 to implement the monitoring and traffic redirection required by the DTN, and a proof-of-concept prototype is presented to validate its functionality. This work identifies a trade-off regarding access to previously unknown external services due to redirection via the DTN until classification is complete, which can introduce significant delays., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

An experimental tethered UAV-based communication system with continuous power supply

  • Rodríguez Ortega, Verónica
  • Tipantuña Tenelema, Christian José
  • Reinoso Chisaguano, Diego Javier
  • Carvajal Rodríguez, Jorge
  • Egas Acosta, Carlos
  • Proaño Chamorro, Pablo Andrés
  • Hesselbach Serra, Xavier
Ensuring reliable communication in remote or disaster-affected areas is a technical challenge due to unplanned deployment and mobilization, meaning placement difficulties and high operation costs of conventional telecommunications infrastructures. To address this problem, unmanned aerial vehicles (UAVs) have emerged as an excellent alternative to provide quick connectivity in remote or disaster-affected regions at a reasonable cost. However, the limited battery autonomy of UAVs restricts their flight service time. This paper proposes a communication system based on a tethered UAV (T-UAV) capable of continuous operation through a wired power network connected to a ground station. The communications system is based on low-cost devices, such as Raspberry Pi platforms, and offers wireless IP telephony services, providing high-quality and reliable communication. Experimental tests assessed power consumption, UAV stability, and data transmission performance. Our results prove that the T-UAV, based on a quadcopter drone, operates stably at 16 V and 20 A, ensuring consistent VoIP communications at a height of 10 m with low latency. These experimental findings underscore the potential of T-UAVs as cost-effective alternatives for extending or providing communication networks in remote regions, emergency scenarios, or underserved areas., This work is part of the I+D+i project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER, UE. Escuela Politécnica Nacional supported this work through the project PIIF-24-06., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A novel architecture for virtual network twin deployment

  • Banisadr, Amir Hossein
  • Hesselbach Serra, Xavier
In this paper, a novel architecture is proposed that enhances network connectivity by combining network virtualization and the digital twin approach. A virtual network twin (VNT) framework is designed to emulate the behavior of the original network within a virtualized environment. This framework provides an enhanced connection experience for users, mirroring the performance of the original network while avoiding the limitations of previous methods such as Telnet, SSH, and VPN. By integrating the network virtualization approach and the concept of digital twins, this framework can improve network visibility, security, and robustness in real-time connectivity through appropriate communication protocols and artificial intelligence (AI) methods. The application of this proposal can significantly impact key areas such as medical applications, autonomous driving, and space communications. This paper introduces the VNT architecture; its core components; requirements; and evaluation metrics, such as the accuracy of the VNT., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Building a 5G-TSN testbed: architecture and challenges

  • Agustí Torra, Anna
  • Ferré Mancebo, Marc
  • Rincón Rivera, David
  • Cervelló Pastor, Cristina
  • Sallent Ribes, Sebastián
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Time-Sensitive Networking (TSN) is one of the best networking technologies currently available for industrial communications, due to its strict Quality-of-Service (QoS) guarantees. TSN defines several mechanisms, where packet schedulers play the most important role. The Time-Aware Shaper (TAS) is the scheduler best suited for industrial scenarios, since it is able to assign periodic timeslots to specific flows, thus ensuring QoS if routing and scheduling are correctly configured by the Software-Defined Networking (SDN)-based TSN control plane. However, TSN is a wire-based technology that lacks the flexibility and mobility provided by wireless technologies such as 5G. This is why 3GPP, starting from Release 16, has defined an architecture for the integration of (typically private) 5G networks and TSN in industrial scenarios. New elements, called TSN Translators (TTs), are needed between the 5G and TSN data planes, and an interface, named TSN Application Function (AF), is defined in 5G to communicate the control planes of both networks. This paper describes the architecture, challenges, and preliminary results obtained from a 5G-TSN network testbed (including TSN equipment and 5G emulators, and an SDN-based control plane)., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union - NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15– 6GSMART-EZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/50110001103, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura::9.4 - Per a 2030, modernitzar les infraestructures i reconvertir les indústries perquè siguin sostenibles, usant els recursos amb més eficàcia i promovent l’adopció de tecnologies i processos industrials nets i racionals ambiental­ment, i aconseguint que tots els països adoptin mesures d’acord amb les capacitats respectives, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Aproximación hacia arquitecturas modulares asistidas por computación en el borde para optimización de comunicaciones holográficas

  • Castillo Gómez-Raya, Genís
  • Fernández Langa, Sergi
  • Rincón Rivera, David
  • Montagud Climent, Mario
Este artículo presenta una aproximación inicial hacia arquitecturas modulares asistidas por computación en el borde (Edge Computing) orientadas a una optimización de la prestación de servicios de comunicaciones holográficas multiusuario. Se propone una modularización de componentes y módulos en el lado servidor que, por una parte, permite desacoplar el plano de control del plano de datos de usuario y, por otra parte, facilita una gestión dinámica de conexiones en función de requerimientos específicos y a los recursos disponibles. La arquitectura propuesta, junto con sus mecanismos de orquestación asociados, se adapta y reconfigura mediante la especificación e integración de APIs de red compatibles con iniciativas de estandarización actuales. Los beneficios de esta aproximación se validan preliminarmente a través de pruebas experimentales que evidencian, por un lado, las ventajas de utilizar servidores de borde para la gestión de comunicaciones, y por otro, el impacto positivo del balanceo de carga entre componentes servidor en cuanto a la escalabilidad y estabilidad del servicio., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A microservices-based control plane for time-sensitive networking

  • Agustí Torra, Anna
  • Ferré Mancebo, Marc
  • Orozco Urrutia, Gabriel David
  • Rincón Rivera, David
  • Remondo Bueno, David
Time-Sensitive Networking (TSN) aims to provide deterministic communications over Ethernet. The main characteristics of TSN are bounded latency and very high reliability, thus complying with the strict requirements of industrial communications or automotive applications, to name a couple of examples. In order to achieve this goal, TSN defines several scheduling algorithms, among them the Time-Aware Shaper (TAS), which is based on time slots and Gate Control Lists (GCLs). The configuration of network elements to allocate time slots, paths, and GCLs is laborious, and has to be updated promptly and in a dynamic way, as new data flows arrive or disappear. The IEEE 802.1Qcc standard provides the basis to design a TSN control plane to face these challenges, following the Software-Defined Networking (SDN) paradigm. However, most of the current SDN/TSN control plane solutions are monolithic applications designed to run on dedicated servers, and do not provide the required flexibility to escalate when facing increasing service requests. This work presents 𝜇 TSN-CP, an SDN/TSN microservices-based control plane, based on the 802.1Qcc standard. Our architecture leverages the advantages of microservices, enabling the control plane to scale up or down in response to varying workloads dynamically. We achieve enhanced flexibility and resilience by breaking down the control plane into smaller, independent microservices. The performance of 𝜇 TSN-CP is evaluated in a real environment with TSN switches, and various integer linear problem solvers, running over different computing platforms., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Multi-agent reinforcement learning-based routing and scheduling models in time-sensitive networking for internet of vehicles communications between transportation field cabinets

  • Garcia Cantón, Sergi
  • Ruiz de Mendoza, Carlos Ausias
  • Cervelló Pastor, Cristina
  • Sallent Ribes, Sebastián
Future autonomous vehicles will interact with traffic infrastructure through roadside units (RSUs) directly connected to transportation field cabinets (TFCs). These TFCs must be interconnected to share traffic information, enabling infrastructure-to-infrastructure (I2I) communications that are reliable, synchronous and capable of transmitting vehicle data to the Internet. However, I2I communications present a complex optimization challenge. This study addresses this by proposing the design, implementation, and evaluation of an automated management model for I2I service channels based on multi-agent reinforcement learning (MARL) integrated with deep reinforcement learning (DRL). The proposed models efficiently manage the routing and scheduling of data frames between internet of vehicles (IoV) infrastructure devices through time-sensitive networking (TSN) to ensure real-time synchronous I2I communications. The solution incorporates both a routing model and a scheduling model, evaluated in a simulated shared environment where agents operate within the TSN control plane. Both models are tested for different topologies and background traffic levels. The results demonstrate that the models establish the majority of paths in the scenario, adhering to near-optimal routing and scheduling policies. Recursively, for each individual request to create a service channel, the system establishes online an optimal synchronous path between entities with a limited time budget. In total, 71% of optimal routing paths are established and 97% of optimal schedules are achieved. The approach takes into account the periodic nature of the transmitted data and its robustness through TSN networks, obtaining 99 percent of compliant service requests with flow jitter levels below 100 microseconds for different topologies and different network utility percentages. The proposed solution achieves lower execution delays compared to the iterative ILP approach. Additionally, the solution facilitates the integration of 5G networks for vehicle-to-infrastructure (V2I) communications, which is identified as an area for future exploration., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union—NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15–6GSMART-EZ), as well as by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/50110001103., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Deep reinforcement learning-based joint scheduling and routing for Time-Sensitive Networks

  • Garcia Cantón, Sergi
  • Cervelló Pastor, Cristina
  • Rincón Rivera, David
  • Sallent Ribes, Sebastián
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., In the deployment of 5G and the development of the future 6G, a set of use cases are generated that require URLLC (Ultra-Reliable Low Latency communications) service-type communications with very low latency and extremely high reliability. At the same time, verticals such as Industry 4.0 require Key Performance Indicators (KPIs) that can only be offered by deterministic networks. Time Sensitive Networking (TSN) is a set of IEEE 802.1 standards that aim to provide highly reliable, low-latency deterministic communications over Ethernet. The IEEE 802.1Qcc standard defines three architectural models for TSN networks. One of them is fully centralized, which is based on an SDN architecture where the control plane is distributed between two entities: the Centralized Network Configuration (CNC) and the Centralized User Configuration (CUC). These systems' increasing complexity and scalability led to the introduction of Machine Learning (ML) tools that will allow them to move towards zero-touch. Currently, solutions are proposed using Integer Linear Programming (ILP), whose computational complexity implies a significant lack of scalability, which worsens as the network size or traffic heterogeneity increases. This paper describes a traffic scheduling and routing algorithm based on deep reinforcement learning (DRL), which is located in the CNC, receiving requests from CUC users and configuring and maintaining the Gate Control lists of the Ethernet switches. The proposed mechanism jointly solves a deterministic routing of data flows with scheduling. This proposal also optimizes the load balancing of the links and the occupation of the time slots of each link., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union— NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15– 6GSMART-EZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/50110001103., Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura::9.4 - Per a 2030, modernitzar les infraestructures i reconvertir les indústries perquè siguin sostenibles, usant els recursos amb més eficàcia i promovent l’adopció de tecnologies i processos industrials nets i racionals ambiental­ment, i aconseguint que tots els països adoptin mesures d’acord amb les capacitats respectives, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Performance evaluation methodology for federated XR network digital twins in AI-aware 6G networks

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier
Network digital twins (NDTs) are emerging as key enablers of 6G networks integrating artificial Intelligence (AI) techniques. NDT systems offer novel features, including real-time monitoring, simulation, enhanced network planning, autonomous management, seamless integration with emerging technologies such as extended reality (XR), among others. When NDTs converge with XR, NDTs can be customized with additional interactive services that are not available in the original network. In this work, artificial intelligence (AI) strategies are applied to a set of XR functions within federated NDTs. While existing NDT approaches follow a one-to-one (1:1) model, where a single NDT instance is deployed from an original network, the one-to-many (1:N) federation model requires the orchestration of multiple XR-tailored NDT instances. The federation of NDTs can be applied across diverse 6G use cases, including telemedicine, UAV management, Industry 4.0, and the remote driving of complex vehicles. Ensuring the optimal operation of the NDT federation requires a methodology tailored to the requirements of each use case. This paper introduces a score-based performance analysis to quantify the benefits achieved through NDT federation. Unlike existing models for the digital twin (DT) federation, this paper introduces a KPI-based rational model that quantifies the trade-off between federation benefits and the associated operational complexity. A mathematical analysis is performed to validate the consistency of the score formula both in general terms and within the context of each specific use case., This work is part of the I+D+i project PID2022-137329OB-C41 and supported by MICIU/AEI/10.13039/501100011033 and FEDER, UE., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Digital Twin Networks requirements: towards an ultra-reliable infrastructure

  • Hesselbach Serra, Xavier
  • Calle Heredia, Xavier Ezequiel
Digital Twin Networks (DTNs) enable a new generation of applications, ranging from medical, social and spatial communications. The deployment demands ultra-reliable, high-speed, and latency-aware network infrastructure to provide synchronization and integrity, requiring massive data transmission. As DTNs scales, challenges such as bandwidth constraints, latency and network reliability become critical. This paper explores the evolving network requirements of DTNs, highlighting key challenges and potential solutions for several scenarios. Addressing these demands is essential for ensuring seamless DTN operations., This work has been supported by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/ MCIN/ AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Qubit rate modulation-based time synchronization mechanism for multi-node quantum networks

  • Jofre Cruanyes, Marc
The combination of quantum and telecommunication networks enables to revolutionize the way information is used, offering unparalleled capabilities and making it an ideal choice for many critical applications. In this sense, quantum protocols generally have a unique requirement to have strict time synchronization in order to operate, which generally consume quantum resources of part of the exchanged qubits. Accordingly, work demonstrates and characterizes a temporal alignment mechanism for quantum networks based on frequency testing, allowing to preserve the quantum state of qubits. The time synchronization correction achieved is within 100 ns working at 5 MHz with temporal and relative frequency offsets commonly acquired in quantum links using conventional hardware clocks with temporal stability in the range of 10-8 and 200-ns jitter., This work was supported in part by the Agencia Estatal de Investigación (Spain) under Grant PID2022-137329OB-C41, Grant PID2022-136869NB-C31 (MCIN/AEI/10.13039/501100011033/FEDER, UE), Grant CNS2024-154600, and Grant PDC2022-133091-I00, in part by the Catalan Government University and Research Aid Management Agency (AGAUR) with Research Group under Grant 2021 SGR 01046, and in part by the Technical University of Catalonia (UPC) under Grant ALECTORS 2024., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Precision time protocol synchronization analysis for single and coincidence qubit detection in quantum networks

  • Jofre Cruanyes, Marc
  • Saigi, Ferran
  • Rincón Rivera, David
2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The combination of Quantum and Telecommunications networks, offering unparalleled quantum correlation-based capabilities and making it an ideal choice for certain critical applications, requires precise time synchronization across network nodes. This work analytically and experimentally assessed the application of the IEEE 1588 Precision Time Protocol in achieving time synchronization within quantum networks. As results, operating at a repetition rate of 5MHz, the overall time synchronization precision is 65ns for single-qubit detection and 100ns for double-fold coincidence measurements. Correspondingly, the experimental results highlight the role of time-synchronization precision protocols in multi-node quantum networks and also provide insights for further developments for scalable quantum network infrastructure., This work was financially supported by PID2022-137329OB-C41 and PID2022-136869NB-C31 (MCIN / AEI / 10.13039 / 501100011033 / FEDER, UE), CNS2024-154600, PDC2022-133091-I00, grants of the Agencia Estatal de Investigaci´ on (Spain), Catalan Government University and Research Aid Management Agency (AGAUR) with Research Group grant 2021 SGR 01046, and ALECTORS 2024 grant from Universitat Polit` ecnica de Catalunya- BarcelonaTech (UPC)., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Digital twin-driven virtual network architecture for enhanced extended reality capabilities

  • Calle Heredia, Xavier Ezequiel
  • Hesselbach Serra, Xavier
Extended Reality (XR) technology is proposed as a key enabler for the development of immersive applications, thus transforming the way users interact within digital environments. In communication networks, XR will be able to introduce immersive network functions with the potential to enhance the network experience. This paper proposes a comprehensive architectural framework designed to support the deployment of XR Functions (XRFs) within a Digital Twin Network (DTN) environment in order to provide immersive functions of any type, including control and management functions, that are not available in the original network. The proposal can be deployed in relevant fields where digital twins are promising, such as medical applications, surveillance systems, autonomous driving and space communications. The proposed architecture must consider the need for minimal hardware and software resources, along with a network topological configuration with the objective of providing a robust yet lightweight framework, allowing devices with limited computing power, such as smartphones and laptops, to benefit from the enhanced network functionalities provided in the Digital Twin Network, without affecting the original network (ON)., This workhasbeensupportedbytheAgenciaEstataldeInvestigación ofMinisterio de Ciencia e Innovación of Spain under project PID2022-137329OB-C41/MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

An intent conflict detection and resolution model for transport connectivity services

  • Alemany, Pol
  • Niknahad, Hadi
  • Adanza, Daniel
  • Díaz Rivera, Javier José
  • Gifré Renom, Lluis
  • Rincón Rivera, David
  • Vilalta, Ricard
  • Muñoz, Raul
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper presents a solution for detecting and resolving conflicts in Intent-Based Networking (IBN) for transport connectivity services. As networks become more complex, IBN allows high-level, goal-oriented management, but conflicts between overlapping intents can degrade performance or security. The paper proposes a two-level conflict detection model—within a single intent (intra-intent) and between multiple intents (inter-intent)—focusing on key service quality attributes like latency, bandwidth, and packet loss. A resolution model combines priority-based allocation and weighted fair sharing to ensure fair resource distribution. The solution was validated using the ETSI TeraFlow SDN controller, showing fast conflict detection and resolution, typically within milliseconds. The results confirm its effectiveness for real-time network management in dynamic environments like IoT and 5G, 6G and beyond., This work is partially funded by the EC through the ACROSS (101097122) project, partially by the Ministerio de Asuntos Económicos y Transformación Digital and the European Union-Next GenerationEU in the frameworks of the Plan de Recuperación, Transformación y Resiliencia and of the Mecanismo de Recuperación y Resiliencia through UNICO-5G I+D 6GMICROSDN project under references TSI-063000-2021-19, TSI-063000-2021-20, TSI063000-2021-21, and the MCIN/AEI/10.13039/501100011033/FEDER/UE, and by the RELAMPAGO project (Grant PID2021-127916OB-I00) funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU, and by the project 6G-INSPIRE PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER (EU)., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A simulator for testing and developing scheduling mechanisms in integrated 5G/6G-TSN scenarios

  • Agustí Torra, Anna
  • Sierra Guerrero, Cilia Ines
  • Jofre Cruanyes, Marc
  • Rincón Rivera, David
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Time-Sensitive Networking (TSN) is an Ethernetbased technology that provides Quality-of-Service (QoS) guarantees, making it ideal for industrial communications. The 3GPP has designed scenarios where 5G (and future 6G) networks integrate with TSN in industrial deployments, adding mobility and flexibility to wire-based TSN networks. In this context, TSN scheduling mechanisms play an important role. This paper presents a simulator developed to test scheduling mechanisms for TSN controllers. The basic operation of the simulator is presented. Finally, preliminary results obtained using the two scheduling mechanisms currently implemented are described., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union—NextGenerationEU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, ref. number TSI-063000-2021-15–6GSMARTEZ), and by the Agencia Estatal de Investigación of Ministerio de Ciencia e Innovación of Spain under I+D+i project PID2022-137329OB-C41, supported by MICIU/AEI/10.13039/501100011033 and FEDER (EU), Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Reinforcement learning and multi-access edge computing for 6G-Based underwater wireless networks

  • Cepeda Pacheco, Juan Carlos
  • Domingo Aladrén, Mari Carmen
6G networks are envisioned to dramatically enhance the connectivity landscape by integrating communication across ground, air, and sea environments. In the aquatic domain, the Internet of Underwater Things (IoUT) represents a global network of intelligent underwater devices designed to capture, interpret, and share data. Although Underwater Acoustic Communications (UAC) has become widespread as a solution for transmitting information, data collection from Underwater Sensor Nodes (USNs) to the surface results in extensive delays and higher energy consumption. Edge communication emerges as a solution to address these challenges. In this approach, Autonomous Underwater Vehicles (AUVs) bring edge computing as close as possible to the source devices. This paper proposes an innovative AUV-based Multi-Access Edge Computing (MEC) system where cluster-heads that collect data from IoUT devices offload their associated computational tasks to local AUVs. These AUVs are strategically positioned to execute tasks either fully locally, partially, or by offloading them entirely to a more resource-equipped AUV (AUV MEC). We achieve this by jointly optimizing the task offloading strategy, resource allocation, and the trajectories of the AUVs. We formulate a non-convex optimization problem to minimize the weighted sum of service delays for all local AUVs and their energy consumption. To address the NP-hard nature of this problem, we employ a deep reinforcement learning algorithm, Deep Deterministic Policy Gradient (DDPG), to solve it. Extensive simulations have been conducted to evaluate the effectiveness of our proposed communication system. The results show that our proposed algorithm outperforms the Total Offloading (Offloading), Local Execution (Locally), and Actor-Critic (AC) algorithms., Postprint (published version)