Skip to main content

INVESTIGACION EN FUTURAS REDES TOTALMENTE OPTIMIZADAS MEDIANTE INTELIGENCIA ARTIFICIAL-B

PID2020-118011GB-C22

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2020
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 56
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Probabilistic constellation shaping in flex-grid over multicore fibre optical backbone networks: an energy savings evaluation

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Cho, Junho
  • Spadaro, Salvatore|||0000-0002-4100-1726
Probabilistic constellation shaping (PCS) has been shown to close the gap to channel capacity at any distance, by providing a fine-grained software-defined trade-off between achievable spectral efficiency and transmission reach. Previous works on PCS performance evaluation in Flex-Grid over multicore fibre optical backbone networks have already noted its superior performance when compared to traditional modulation formats, as well as its potential to lower associated network capital expenditures (CAPEX) by allowing, for example, a reduction in the required number of transceivers to handle the offered traffic demands. This paper investigates the potential of PCS to lower network energy consumption, as a way to contribute to the eco-friendliness and sustainability of next-generation optical backbone networks. © 2024 IEEE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

The role of the TSN controller in E2E deterministic services provisioning

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Pagès Cruz, Albert|||0000-0002-6661-3630
The provisioning of deterministic services over E2E multi-technological infrastructures requires the proper configuration of the resources to match the required Key Performance Indicators (KPI), such as latency and jitter. From an architectural point of view, such configuration is carried out by an SDN-based TSN Controller that has the responsibility to control multiple technologies. In this paper, the main challenges of the TSN controller in such scenario are deeply discussed and its role and implementation in the TIMING architecture is also discussed., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and TIMING (TSI-063000-2021-145) funded by MCIN and NextGenerationEU/PRTR., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

On the challenges of optical disaggregated data center networking for ML/AI applications

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
The rising of applications with intense requirements in data volumes, storage space and CPU/GPU utilization, such as Machine Learning/Artificial Intelligence (ML/AI) applications, imposes different challenges on the Data Center Network design and operation. When compared to traditional data centers infrastructures, the recent explored disaggregated optical data center concept may bring multiple benefits in terms of optimized usage of the IT and network resources. Nevertheless, at the same time, it also brings some technical challenges. In such context, the paper discusses both data and control architectural solutions for optical disaggregated data centers for ML/AI applications, focusing on their benefits but also on the associated complexities., This publication is supported by the project TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

KPI-aware service provisioning for remote industrial control systems management

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Guasch Mesià, Enric
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
The advent of B5G/6G communication infrastructures answers to the requirements posed by emerging use cases and business models, such as Industry 4.0 and autonomous guided vehicles, which impose a set of highly demanding Key Performance Indicators (KPIs). In this regard, time-engineered applications are of particular importance. Said applications, while do not may impose very demanding latencies, they impose a strict control over them to ensure a deterministic service performance. This has given rise to the concept of Deterministic Networking that relies on adding deterministic capabilities to all involved network infrastructures. In general, optical networks are seen as one of the main enablers of latency and jitter-bounded communications, due to their intrinsic deterministic nature. In the framework of Industry 4.0 use cases, such capability can be exploited to enable remote control of optically interconnected smart factories, contributing this way to reduce both CAPEX and OPEX. However, the estimation of KPIs across optically interconnected smart factories/client domains and the provisioning of end-to-end (E2E) services arises several challenges. In this work, we present firstly multiple service provisioning schemas (single-vs multi-path) leveraging the capabilities of the Software Defined Networking (SDN) paradigm. Then, we provide tools and algorithms for best-case KPI estimation and resource allocation decision and analyze the impact of supporting heterogeneous KPIs into the obtained overall network performance., This publication is supported by the project TRAINER-B (PID2020- 118011 GB-C22) funded by MCIN/AEI/10.13039/501100011033 and the by the European Commission through Grant No. 101095890 (Predict-6G project)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Evaluation of probabilistic constellation shaping performance in Flex Grid over multicore fiber dynamic optical backbone networks [Invited]

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Spadaro, Salvatore|||0000-0002-4100-1726
In this paper, we present a worst-case methodology for estimating the attainable spectral efficiency over end-to-end paths across a Flex Grid over multicore fiber (MCF) optical network. This methodology accounts for physical link noise, as well as for the signal-to-noise ratio in the Add module (SNR TX ) of spatial-division-multiplexing-enabled reconfigurable optical add and drop multiplexers (SDM-ROADMs), introducing a dominant noise contribution over that of their Bypass and Drop modules. The proposed methodology is subsequently used to quantify the benefits that probabilistic constellation shaping (PCS) can bring to Flex-Grid/MCF dynamic optical backbone networks, compared to using traditional polarization-multiplexed modulation formats. In a first step, insight is provided into the spectral efficiency attainable along the precomputed end-to-end paths in two reference backbone networks, either using PCS or traditional modulation formats. Moreover, in each one of these networks, two SNR TX values are identified: the SNR TX yielding the maximum average paths’ spectral efficiency, as well as an SNR TX that, although slightly degrading the average paths’ spectral efficiency (by 10%), would yet enable a cost-effective SDM-ROADM Add module implementation. Extensive simulations are conducted to analyze PCS offered load gains under 1% bandwidth blocking probability. Furthermore, the study lastly focuses on finding out whether lower fragmentation levels in Flex-Grid/MCF dynamic optical backbone networks can push PCS benefits even further., Funding: Agencia Estatal de Investigación (PID2020-118011GB-C21, PID2020-118011GB-C22, RED2018-102585-T)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

On the path computation for E2E deterministic services in future 6G networks

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Guasch, Enric
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
Future 6G systems and networks will need to provide support to a wide set of highly demanding use cases. Among others, service provisioning with deterministic guarantees, such as latency and jitter must be supported in SDNcontrolled networks. In an E2E scenario, the selection of the paths over the different involved technological domains must be done properly to assure the service guarantees. In this paper, the role of the Path Computation (PC) in an SDN-based control architecture for deterministic services is firstly discussed. E2E Paths selection strategies are then benchmarked., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and by the European Commission through Grant No. 101095890 (Predict- 6G project), Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Low-cost all-optical switching nodes for ultra-dense optical metro-access networks

  • Sarmiento Hernández, Samael|||0000-0001-6549-8426
  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
Optical metro-access networks (OMANs) must enable the connectivity among 5G-based radio stations, edge datacentres, businesses, and home users. In such a heterogenous scenario, greater scalability, higher levels of dynamic connectivity and flexibility, reduced end-to-end latency, and increased energy efficiency are required. Mesh-based ultra-dense wavelength division multiplexing (u-DWDM) OMANs using reconfigurable optical switching nodes are a promising solution. However, the designs of traditional optical switching nodes relay on wavelength-selective switches (WSSs), which provide high network reconfigurability only at a high cost, making them prohibitive for OMANs. Moving away from this design approach, we proposed a novel low-cost and energy-efficient design based on a modular DWDM structure for reconfigurable optical add-drop multiplexer (ROADM) and optical cross-connects (OXC) nodes compatible with mesh-based u-DWDM OMANs. Results show that proposed solutions can provide performance close to that of WSS-based OXCs but with a switching node cost reduction of one order magnitude., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Open-source 5G digital twin: Virtualizing core and RAN for network replication

  • Rodrigues Dos Santos, Cristhian Jose
  • Mateos Pérez, Izan
  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
  • Anguera Lo, Joan
  • Umbert Juliana, Anna|||0000-0001-7825-5212
This paper presents a proposed methodology for creating digital twins of 5G networks using open-source 5G core and Radio Access Network (RAN) implementations. Our research will demonstrate how virtualized network functions can be deployed to create accurate digital replicas of operational 5G infrastructures. We will evaluate three leading open-source 5G core implementations—Open5GS, free5GC, and OpenAir-Interface—assessing their performance characteristics and suitability for digital twin applications. The proposed architecture will specifically replicate a distributed multi-campus research network, featuring multiple gNodeB units at each location connected through IP transport networks to Compact Mobility Units (CMUs) that bundle core network functions. Our implementation will enable bi-directional synchronization between physical networks and their digital counterparts, facilitating testing, optimization, and AI/ML model training without disrupting operational environments. Performance benchmarks and implementation guidelines provided in this paper will contribute to the growing field of network digital twins, offering a cost-effective approach for creating high-fidelity network replicas using open-source tools., This work has been partially financed by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation program Grant Agreement No. 101139182, 6GEWOC, and Spanish MICIU founded, TRAINER-B (PID2020-118011GBC22) and MTDFP project ELEGANT (TSI-064100-2023-0009)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

On the benefits of optical disaggregated datacentre infrastructures for machine learning applications

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
ML applications present time varying requirements that should be accounted for an optimized deployment. We evaluate the benefits of disaggregated DC infrastructures for supporting them and propose a dynamic re-orchestration strategy for improved resource usage., This publication is supported by the project TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Reducing the number of transceivers with probabilistic constellation shaping in flex-grid over MCF optical backbone networks

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Cho, Junho
  • Spadaro, Salvatore|||0000-0002-4100-1726
This paper quantifies the potential reduction in the number of required transceivers that the use of probabilistic constellation shaping (PCS) can bring to Flex-Grid over multicore fiber (MCF) optical backbone networks, which can directly lead to a reduction in network capital expenditure (CAPEX). Results from two different backbone networks illustrate that PCS can significantly decrease the number of required transceivers compared to using traditional modulation formats, thanks to the finer granularity in spectral efficiency. The observed reduction becomes more prominent (up to 22.3%) as the traffic profile bit-rates and the network physical distances increase., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Evaluating the impact of the guard band width on the benefits of probabilistic constellation shaping in future flex-grid over multicore fibre optical backbone networks

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Cho, Junho
  • Spadaro, Salvatore|||0000-0002-4100-1726
Probabilistic constellation shaping (PCS) has emerged as an advanced modulation technique that provides a fine-grained software-defined trade-off between achievable spectral efficiency (SE) and transmission reach to deliver optimal channel capacity at any distance. This paper quantifies the network throughput benefits resulting from adopting PCS in future Flex-Grid over multicore fibre optical backbone networks, compared to using traditional uniform modulation formats. In particular, different inter-channel guard band width configurations are accounted in our study, aiming to set guidelines on the technological requirements imposed to network spectrum selective switches (SSS) to take full PCS advantage in future optical backbone networks., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Joint communication and sensing for connected vehicles with commercial devices

  • Sánchez Alcántara, Andrés
  • Dios Otín, Víctor Federico|||0000-0002-6720-8514
  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
  • Pinazo Donoso, Jorge
  • Lerín, Adolfo
The development of devices that integrate sensing and communication is an area of increasing interest in research on connectivity systems for autonomous vehicles. This paper experimentally implements this concept using commercial radars. By utilizing the capabilities of two radars designed exclusively for sensing, the radar signals are modulated in such a way that one radar can transmit encoded information about its own sensing data, while the other radar receives, decodes, and analyses the information. The communication showed error free ranging from 0 to 45 m, in an outdoor environment with realistic conditions., This research has been partially financed by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation program Grant Agreement No. 101139182, 6G-EWOC and Spanish MICIU founded, TRAINER-B (PID2020- 118011GB-C22)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Phase noise reduction in continuous-variable quantum key distribution using digital filtering

  • Sarmiento Hernández, Samael|||0000-0001-6549-8426
  • Llanos Pla, Elisabeth
  • Adillon Albero, Pol
  • Tabares Giraldo, Jeison
  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
  • Etcheverry, Sebastian
Quantum key distribution (QKD) enables information-theoretic-secure secret key exchange thanks to the laws of quantum mechanics. Since it can easily be incorporated into existing telecom networks, continuous-variable QKD (CV QKD) using coherent states and coherent detection has recently emerged as a promising candidate. However, the secret key rate and link distance in CV QKD systems are still limited by the imperfections of used components. In this work, through simulations, we study the use of different digital filtering techniques for optical phase recovery, aided by pilot symbols, to mitigate the phase noise induced by the coherent mixing of two free-running lasers in a CV QKD system. Moving average, Butterworth and unscented Kalman filters are evaluated for different phase drift conditions. Results show that phase recovery from small amplitude pilot symbols, along with further digital filtering, can considerably reduce phase noise and measurement error, while increasing the secret key rate and link distance of the CV QKD system., This work was supported in part by the European Union through the Digital Europe Work Programme 2021-2022 [DIGITAL-2021-QCI-01- INDUSTRIAL/QuarterProject/101091588], Spanish Ministry Grants PTQ2021-012121, PTQ2021-012123 and TRAINER-B (PID2020- 118011GB-C22), funded by [MCIN/AEI/10.13039/ 50110001103], as well as Pla de Doctorats Industrials del Departament de Recerca i Universitats de la Generalitat de Catalunya under Grants 2022-DI-0118 and 2023-DI-0052., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Machine learning-based actuation orchestration for inter-/intra-data center networks

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
Datacenter (DC) infrastructures are essential to support the requirements posed by nowadays digital society and emerging industrial trends. In such context, a proper actuation management has become especially relevant for service quality assurance operations. In situations where it may be difficult to determine which is the sub-system that needs to apply an actuation, machine learning (ML)-based strategies become valuable assets to orchestrate the actuations to be applied. In this paper, we discuss three strategies for actuation orchestration in inter-/intra-DC scenarios interconnected through optical network systems and benchmark them in terms of requirements that they impose and the achieved performance, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Unveiling the potential of graph neural networks for robust intrusion detection

  • Pujol Perich, David
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
The last few years have seen an increasing wave of attacks with serious economic and privacy damages, which evinces the need for accurate Network Intrusion Detection Systems (NIDS). Recent works propose the use of Machine Learning (ML) techniques for building such systems (e.g., decision trees, neural networks). However, existing ML-based NIDS are barely robust to common adversarial attacks, which limits their applicability to real networks. A fundamental problem of these solutions is that they treat and classify flows independently. In contrast, in this paper we argue the importance of focusing on the structural patterns of attacks, by capturing not only the individual flow features, but also the relations between different flows (e.g., the source/destination hosts they share). To this end, we use a graph representation that keeps flow records and their relationships, and propose a novel Graph Neural Network (GNN) model tailored to process and learn from such graph-structured information. In our evaluation, we first show that the proposed GNN model achieves state-of-the-art results in the well-known CIC-IDS2017 dataset. Moreover, we assess the robustness of our solution under two common adversarial attacks, that intentionally modify the packet size and interarrival times to avoid detection. The results show that our model is able to maintain the same level of accuracy as in previous experiments, while state-of-the-art ML techniques degrade up to 50% their accuracy (F1-score) under these attacks. This unprecedented level of robustness is mainly induced by the capability of our GNN model to learn flow patterns of attacks structured as graphs., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), and by the European Union’s Horizon 2020 research and innovation programme within the framework of the NGI-POINTER Project, funded under grant agreement No. 871528. This article reflects only the authors’ view; the European Commission is not responsible for any use that may be made of the information it contains., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Autonomous resource assignment for optimal utilization in optical data centre infrastructures

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Biosca Caro, Jordi
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
We present an architectural solution based on data analytics for self-organizing optical data centers. Thanks to a reinforcement learning-based cognitive layer, an adaptive and autonomous resource assignment to deployed services is achieved., This work has been supported by the Spanish Government through project TRAINER-B (PID2020‐118011GB‐C22) with FEDER contribution., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Practical spectral efficiency estimation for optical networking

  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Cho, Junho
  • Spadaro, Salvatore|||0000-0002-4100-1726
Assigning the right spectral resources is the key to flex-grid optical networking. Finding the optimal spectral allocation is a daunting task, as there are many variables at play that make accurate network models very complex. From a fiber transmission perspective, several impairments, such as amplified spontaneous emission (ASE) noise from amplifiers or nonlinear interference noise (NLIN) generated through transmission, set a limit on spectral efficiency (SE). From a transceiver perspective, modulation format, signal intensity, and spectral allocation affect the achievable capacity. On top of that, the network conditions are dynamic, causing the channel capacity to change over time. Several models have been proposed to estimate SE, ranging from the simplest to more sophisticated ones. If one is willing to sacrifice a small fraction of accuracy in exchange for a very fast service setup, some bounds can be found to guarantee a static level of service. In this work, we evaluate the degree of inaccuracy introduced by the different strategies and their complexity-accuracy trade-offs., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

On the selection of KPI-aware E2E paths for deterministic services in 6G networks

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Blanco Caamaño, Marta
  • Contreras, Luis Miguel
In the 6G ecosystem, the provisioning of deterministic services with KPI guarantees over multi-technological network domains requires the proper selection of the end-to-end (E2E) paths. Since each technological domain has its own capabilities and resources, in an E2E perspective, the proper selection of the domains to achieve the service KPIs is fundamental. The paper discusses the challenges of the E2E path/domain selection, provides an overall supporting control plane architecture and presents a proof of concept., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/ 501100011033 and by the European Commission through Grant No. 101095890 (Predict-6G project)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Demonstration of a control plane in support of E2E deterministic service provisioning over a multidomain multi-technology 6G network

  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Calvillo Fernández, Alejandro
  • Rico Menendez, David
  • De La Oliva Delgado, Antonio
  • Giardina, Pietro G.
  • Ravalli, Matteo
  • Carcel Cervera, José Luis
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Spadaro, Salvatore|||0000-0002-4100-1726
The use cases associated to the emerging 6G technology demand a dynamic and adaptive network operation capable of addressing the specific requirements of heterogeneous data plane technologies. This demonstration presents the operation of a multi-domain multi-technology control plane architecture designed to provision end-to-end (E2E) connectivity with deterministic performance guarantees. Key innovations highlighted in the demonstration include homogenized configuration of diverse data plane technologies, advanced topology abstraction enabling Key Performance Indicator (KPI)-aware path computation, and the use of digital twin (DT)-based KPI estimation to support deterministic connectivity configuration. These capabilities collectively showcase a promising approach for managing the complexity and performance demands of future 6G networks., This publication is supported by the European Commission through Grant No. 101095890 (Predict-6G project) and the project TRAINER-B (PID2020-118011GBC22) funded by MCIN/AEI/10.13039/ 501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Machine learning-based multi-domain actuation orchestration in support of end-to-end service quality-assurance

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Biosca Caro, Jordi
  • Spadaro, Salvatore|||0000-0002-4100-1726
Service quality assurance is of capital importance in modern cloud and network infrastructures, especially in multi-domain scenarios, where multiple operators collaborate to provide end-to-end (E2E) services. However, due to the dynamics of the multiple infrastructures and deployed services, it may be difficult to identify which domains need to perform (re-)configuration operations, named actuations, to keep the quality of the E2E services. In this regard, Machine Learning (ML) techniques appear as an interesting solution for guiding the actuation systems in multi-domain scenarios. With this in mind, we present a novel approach for self-optimised multi-domain service provisioning, leveraging the capacities of Deep Reinforcement Learning (DRL), with a focus on E2E service quality assurance. Running away from traditional approaches, the presented proposal tries to minimize the number of domains that need to actuate rather than determining the exact domain-specific actuations. We compare our proposal to existing strategies in terms of performance, scalability and applicability in real scenarios., This work has been supported by the Spanish Government through project TRAINER-B (PID2020-118011GB-C22) with FEDER contribution., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

6G-EWOC: Crowdsourced SLAM data fusion for safe and efficient ADAS driving

  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
  • Casas Pla, Josep Ramon|||0000-0003-4639-6904
  • Ruiz Hidalgo, Javier|||0000-0001-6774-685X
  • Cortada Garcia, Martí
  • Martin Pey, Gerard
  • Salavedra Pujol, Judit|||0009-0004-5927-7132
  • Wang, Mingrui
  • Theodoropoulou, Eleni
  • Lyberopoulos, George
  • Garcia Gómez, Pablo
  • Royo Royo, Santiago|||0000-0003-0136-8301
  • Riu Gras, Jordi
  • Marcus, Carina
  • Eriksson, Olof
  • Schrenk, Bernhard
  • Fàbrega Sánchez, Josep Maria
The development of transport infrastructures for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles operating efficiently and safely in congestion-free traffic flows is a major challenge for telecommunications technologies. Simultaneous Localization and Mapping (SLAM) plays a crucial role in ensuring uninterrupted journeys for emergency vehicles and increasing the safety of vulnerable road users in complex traffic scenarios. Accurate SLAM mapping for ADAS systems requires data from different sensor technologies –such as high-resolution cameras or Radio/Light Detection and Ranging (RaDAR/LiDAR)– to be effectively combined or fused. Sensor fusion results in high data throughput and low latency requirements. However, optimal mapping outcomes occur when processing systems fuse data from sensors positioned at diverse locations within the traffic scene. By crowdsourcing diverse sensors, we can multiply the view angles, mitigate occlusions and improve the overall scene coverage. Yet, this approach introduces additional challenges for communication systems within both the vehicles and the infrastructure. Addressing these challenges is essential for seamless development of safe and efficient ADAS driving techniques., This work has received funding from the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation Programme under Grant Agreement No. 101139182, and Spanish MICIU founded, TRAINER-B (PID2020-118011GB-C22)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Control and orchestration solutions for end-to-end time sensitive services in future 6G networks

  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Pagès Cruz, Albert|||0000-0002-6661-3630
The provisioning of time sensitive end-to-end services in future 6G networks imposes multiple technical challenges, spanning from the data plane to the control and orchestration planes. In particular, the automation of the provisioning and maintenance of connectivity services with deterministic constraints over multiple technology/administrative domains requires control and orchestration solutions able to assure the strict time service requirements. In line with that, the paper investigates some requirements imposed to the control and orchestration planes and it also shows potential enabling architectures for end-to-end service guarantees, This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and TIMING (TSI-063000-2021-145) funded by MCIN and NextGenerationEU/PRTR., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

On the complexity of configuration and orchestration for enabling disaggregated server provisioning in optical composable data centers

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
Due to the limitations of traditional data center (DC) architectures, the concept of infrastructure disaggregation has been proposed. DC resources are separated into multiple blades to be exploited independently. As a result, composable DC (CDC) infrastructures are achieved, enhancing the modularity of resource provisioning. However, disaggregation introduces additional challenges that need to be carefully analyzed. One relates to the potential complexity increase on the orchestration and infrastructure configuration that need to be performed when provisioning resources to support services. This aspect is highly influenced by the distribution of resources at the physical infrastructure. As such, when analyzing the performance of a CDC, it becomes essential to also study the related operational complexity of the resource orchestration and configuration phases. Furthermore, the requirements of several tenant services may impose heterogeneous deployments over the shared physical infrastructure in the form of either disaggregated single-server or multi-server distributions. The associated orchestration/configuration cost is again highly influenced by the data plane architecture of the CDC. With these aspects in mind, in this paper, we provide a methodology for analysis of the complexity of resource orchestration for a service deployment and the associated configuration cost in optical CDCs, considering various service deployment setups. A selected set of CDC architectures found in the literature is employed to quantitatively illustrate how the data plane design and service deployment strategies affect the complexity of infrastructure configuration and resource orchestration., This work has been supported by the Spanish Government through project TRAINER-B (PID2020-118011GB-C22) with FEDER contribution., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

SDN-based band-adaptive quality assurance scheme in support of heterogenous B5G services over sliceable multi-band optical networks

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
The rise of traffic intensive services and applications is pushing the limits of conventional single band Wavelength Division Multiplexing (WDM) optical networks. As an answer to this challenge, new data plane technologies are being investigated. Multi-band optical networks have raised as a very interesting candidate due to the potential increased capacity they offer thanks to the exploitation of multiple bands of the optical spectrum. Considering the whole telecom ecosystem, multi-band optical networks will coexist with other technological segments (e.g., Radio Access Network (RAN)) with the aim of provisioning services across the end-to-end infrastructure. With the advent of 5G and beyond 5G (B5G) architectures, novel provisioning paradigms are taking preponderance, such as the case of network slicing, which represents a radical paradigm change with respect to legacy business and provisioning models. As such, proper solutions for supporting network slice provisioning and runtime maintenance at the data plane are required. With this in mind, in this paper we present a control and orchestration architecture for the configuration and maintenance of network slices in multi-band optical networks, in support of B5G end-to-end services. Indeed, quality assurance and maintenance at all levels is seen as a cornerstone in B5G architectures. Thus, proper mechanisms adapted to the nature of the underlying sliceable multi-band data plane are required to ensure the quality of deployed slices. In this regard, we also present a novel band-adaptive protection scheme which takes advantage of the properties of the multi-band data plane so as to enhance the robustness of slices against quality degradations. We showcase the provisioning and maintenance of multi-band optical network slices by means of an experimental demonstration in a real testbed deployed at our premises. In addition, we evaluate the performance of the proposed band-adaptive protection scheme for slice quality assurance in front of other strategies by means of extensive simulation analysis in larger network scenarios., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Optically interconnected disaggregated datacenters in support of ML/AI applications: a failure analysis

  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Spadaro, Salvatore|||0000-0002-4100-1726
Disaggregated datacenters are promising solutions for executing ML applications. One crucial aspect is the application resilience against infrastructure failures. We analyze application affectation and disruption rates in front of various failure patterns., This work has been funded by the MCIN project TRAINER-B (PID2020-118011GB-C22)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Data plane technology-agnostic control and orchestration architecture for optical disaggregated data centers

  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Spadaro, Salvatore|||0000-0002-4100-1726
We propose a novel SDN control and orchestration architecture to provide composed IaaS over optical disaggregated data centers. We experimentally validate intent-based mechanisms that make the architecture independent from the underlying physical infrastructure technology., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

QAM order selection strategy for energy-efficient probabilistic constellation shaping in flex-grid over multicore fiber optical backbone networks

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Gené Bernaus, Joan M.|||0000-0002-1082-9408
  • Cho, Junho
  • Spadaro, Salvatore|||0000-0002-4100-1726
Probabilistic constellation shaping (PCS) has become an attractive technology for future optical networks, able to close the gap to channel capacity at any distance by leveraging its superior fine-grained rate adaptability. In order to get as close as possible to the Shannon limit, PCS selects for any signal-to-noise ratio (SNR) the best performing (square) quadrature amplitude modulation (QAM) constellation and forward error correction (FEC) coding rate. However, higher-order QAM constellations are expected to consume more energy per transmitted bit than lower-order ones. So, we investigate in this paper whether carefully dimensioned SNR margins can lower the usage of higher order QAM constellations for end-to-end optical communications in Flex-Grid over multicore fiber (MCF) optical backbone networks, while still keeping high PCS performance levels. Numerical results obtained in two reference backbone networks disclose very significant reductions on the usage of those higher order QAM constellations when adopting the proposed SNR margins for PCS, at expenses of only minor penalties on the spectral efficiency attainable along the precomputed end-to-end paths., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B, with references PID2020-118011GB-C21 and PID2020-118011GB-C22, funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Optical phased array antenna apodization for lidar in autonomous vehicles

  • Lozano, José
  • Jiménez, Humberto
  • Torres Benito, Sergio
  • Biosca Marrón, Pau
  • Fontanet Albinyana, Bernat
  • Pinazo Donoso, Jorge
  • Lerín, Adolfo
  • Dios Otín, Víctor Federico|||0000-0002-6720-8514
  • Casas Pla, Josep Ramon|||0000-0003-4639-6904
  • Lázaro Villa, José Antonio|||0000-0002-5592-8434
This paper presents the specific design of an Optical Phased Array antenna (OPA) to apodize the emission of a lidar in the context of a project where diverse optoelectronic sensors such as cameras, radars, and commercial lidars are used to provide data in order to fuse them and develop perception for robots as future autonomous vehicles. While mechanical based lidars are already commercially available, this work focuses on designing much more robust and potentially cheaper lidars based on photonic integrated circuits and energy optimization through the apodization of the emission of the OPA., This publication is part of the Spanish I+D+i project: PTAS-20211011, “Percepción Inteligente para los Vehículos Autónomos y Conectados”, INPERCEPT, funded by CDTI/MCIN and TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Joint communication and sensing for connected vehicles with commercial devices

  • Sánchez Alcántara, Andrés
  • Dios Otín, Víctor Federico
  • Lázaro Villa, José Antonio
  • Pinazo Donoso, Jorge
  • Lerín, Adolfo
The development of devices that integrate sensing and communication is an area of increasing interest in research on connectivity systems for autonomous vehicles. This paper experimentally implements this concept using commercial radars. By utilizing the capabilities of two radars designed exclusively for sensing, the radar signals are modulated in such a way that one radar can transmit encoded information about its own sensing data, while the other radar receives, decodes, and analyses the information. The communication showed error free ranging from 0 to 45 m, in an outdoor environment with realistic conditions., This research has been partially financed by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation program Grant Agreement No. 101139182, 6G-EWOC and Spanish MICIU founded, TRAINER-B (PID2020- 118011GB-C22)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Optically interconnected disaggregated datacenters in support of ML/AI applications: a failure analysis

  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
Disaggregated datacenters are promising solutions for executing ML applications. One crucial aspect is the application resilience against infrastructure failures. We analyze application affectation and disruption rates in front of various failure patterns., This work has been funded by the MCIN project TRAINER-B (PID2020-118011GB-C22)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

The role of the TSN controller in E2E deterministic services provisioning

  • Spadaro, Salvatore
  • Agraz Bujan, Fernando
  • Pagès Cruz, Albert
The provisioning of deterministic services over E2E multi-technological infrastructures requires the proper configuration of the resources to match the required Key Performance Indicators (KPI), such as latency and jitter. From an architectural point of view, such configuration is carried out by an SDN-based TSN Controller that has the responsibility to control multiple technologies. In this paper, the main challenges of the TSN controller in such scenario are deeply discussed and its role and implementation in the TIMING architecture is also discussed., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and TIMING (TSI-063000-2021-145) funded by MCIN and NextGenerationEU/PRTR., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Unveiling the potential of graph neural networks for robust intrusion detection

  • Pujol Perich, David
  • Suárez-Varela Maciá, José Rafael
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
The last few years have seen an increasing wave of attacks with serious economic and privacy damages, which evinces the need for accurate Network Intrusion Detection Systems (NIDS). Recent works propose the use of Machine Learning (ML) techniques for building such systems (e.g., decision trees, neural networks). However, existing ML-based NIDS are barely robust to common adversarial attacks, which limits their applicability to real networks. A fundamental problem of these solutions is that they treat and classify flows independently. In contrast, in this paper we argue the importance of focusing on the structural patterns of attacks, by capturing not only the individual flow features, but also the relations between different flows (e.g., the source/destination hosts they share). To this end, we use a graph representation that keeps flow records and their relationships, and propose a novel Graph Neural Network (GNN) model tailored to process and learn from such graph-structured information. In our evaluation, we first show that the proposed GNN model achieves state-of-the-art results in the well-known CIC-IDS2017 dataset. Moreover, we assess the robustness of our solution under two common adversarial attacks, that intentionally modify the packet size and interarrival times to avoid detection. The results show that our model is able to maintain the same level of accuracy as in previous experiments, while state-of-the-art ML techniques degrade up to 50% their accuracy (F1-score) under these attacks. This unprecedented level of robustness is mainly induced by the capability of our GNN model to learn flow patterns of attacks structured as graphs., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), and by the European Union’s Horizon 2020 research and innovation programme within the framework of the NGI-POINTER Project, funded under grant agreement No. 871528. This article reflects only the authors’ view; the European Commission is not responsible for any use that may be made of the information it contains., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Practical spectral efficiency estimation for optical networking

  • Gené Bernaus, Joan M.
  • Perelló Muntan, Jordi
  • Cho, Junho
  • Spadaro, Salvatore
Assigning the right spectral resources is the key to flex-grid optical networking. Finding the optimal spectral allocation is a daunting task, as there are many variables at play that make accurate network models very complex. From a fiber transmission perspective, several impairments, such as amplified spontaneous emission (ASE) noise from amplifiers or nonlinear interference noise (NLIN) generated through transmission, set a limit on spectral efficiency (SE). From a transceiver perspective, modulation format, signal intensity, and spectral allocation affect the achievable capacity. On top of that, the network conditions are dynamic, causing the channel capacity to change over time. Several models have been proposed to estimate SE, ranging from the simplest to more sophisticated ones. If one is willing to sacrifice a small fraction of accuracy in exchange for a very fast service setup, some bounds can be found to guarantee a static level of service. In this work, we evaluate the degree of inaccuracy introduced by the different strategies and their complexity-accuracy trade-offs., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

On the challenges of optical disaggregated data center networking for ML/AI applications

  • Spadaro, Salvatore
  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
The rising of applications with intense requirements in data volumes, storage space and CPU/GPU utilization, such as Machine Learning/Artificial Intelligence (ML/AI) applications, imposes different challenges on the Data Center Network design and operation. When compared to traditional data centers infrastructures, the recent explored disaggregated optical data center concept may bring multiple benefits in terms of optimized usage of the IT and network resources. Nevertheless, at the same time, it also brings some technical challenges. In such context, the paper discusses both data and control architectural solutions for optical disaggregated data centers for ML/AI applications, focusing on their benefits but also on the associated complexities., This publication is supported by the project TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033, Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

QAM order selection strategy for energy-efficient probabilistic constellation shaping in flex-grid over multicore fiber optical backbone networks

  • Perelló Muntan, Jordi
  • Gené Bernaus, Joan M.
  • Cho, Junho
  • Spadaro, Salvatore
Probabilistic constellation shaping (PCS) has become an attractive technology for future optical networks, able to close the gap to channel capacity at any distance by leveraging its superior fine-grained rate adaptability. In order to get as close as possible to the Shannon limit, PCS selects for any signal-to-noise ratio (SNR) the best performing (square) quadrature amplitude modulation (QAM) constellation and forward error correction (FEC) coding rate. However, higher-order QAM constellations are expected to consume more energy per transmitted bit than lower-order ones. So, we investigate in this paper whether carefully dimensioned SNR margins can lower the usage of higher order QAM constellations for end-to-end optical communications in Flex-Grid over multicore fiber (MCF) optical backbone networks, while still keeping high PCS performance levels. Numerical results obtained in two reference backbone networks disclose very significant reductions on the usage of those higher order QAM constellations when adopting the proposed SNR margins for PCS, at expenses of only minor penalties on the spectral efficiency attainable along the precomputed end-to-end paths., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B, with references PID2020-118011GB-C21 and PID2020-118011GB-C22, funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Control and orchestration solutions for end-to-end time sensitive services in future 6G networks

  • Spadaro, Salvatore
  • Agraz Bujan, Fernando
  • Pagès Cruz, Albert
The provisioning of time sensitive end-to-end services in future 6G networks imposes multiple technical challenges, spanning from the data plane to the control and orchestration planes. In particular, the automation of the provisioning and maintenance of connectivity services with deterministic constraints over multiple technology/administrative domains requires control and orchestration solutions able to assure the strict time service requirements. In line with that, the paper investigates some requirements imposed to the control and orchestration planes and it also shows potential enabling architectures for end-to-end service guarantees, This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and TIMING (TSI-063000-2021-145) funded by MCIN and NextGenerationEU/PRTR., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

On the path computation for E2E deterministic services in future 6G networks

  • Spadaro, Salvatore
  • Pagès Cruz, Albert
  • Guasch, Enric
  • Agraz Bujan, Fernando
Future 6G systems and networks will need to provide support to a wide set of highly demanding use cases. Among others, service provisioning with deterministic guarantees, such as latency and jitter must be supported in SDNcontrolled networks. In an E2E scenario, the selection of the paths over the different involved technological domains must be done properly to assure the service guarantees. In this paper, the role of the Path Computation (PC) in an SDN-based control architecture for deterministic services is firstly discussed. E2E Paths selection strategies are then benchmarked., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033 and by the European Commission through Grant No. 101095890 (Predict- 6G project), Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Machine learning-based multi-domain actuation orchestration in support of end-to-end service quality-assurance

  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Biosca Caro, Jordi
  • Spadaro, Salvatore
Service quality assurance is of capital importance in modern cloud and network infrastructures, especially in multi-domain scenarios, where multiple operators collaborate to provide end-to-end (E2E) services. However, due to the dynamics of the multiple infrastructures and deployed services, it may be difficult to identify which domains need to perform (re-)configuration operations, named actuations, to keep the quality of the E2E services. In this regard, Machine Learning (ML) techniques appear as an interesting solution for guiding the actuation systems in multi-domain scenarios. With this in mind, we present a novel approach for self-optimised multi-domain service provisioning, leveraging the capacities of Deep Reinforcement Learning (DRL), with a focus on E2E service quality assurance. Running away from traditional approaches, the presented proposal tries to minimize the number of domains that need to actuate rather than determining the exact domain-specific actuations. We compare our proposal to existing strategies in terms of performance, scalability and applicability in real scenarios., This work has been supported by the Spanish Government through project TRAINER-B (PID2020-118011GB-C22) with FEDER contribution., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

SDN-based band-adaptive quality assurance scheme in support of heterogenous B5G services over sliceable multi-band optical networks

  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
The rise of traffic intensive services and applications is pushing the limits of conventional single band Wavelength Division Multiplexing (WDM) optical networks. As an answer to this challenge, new data plane technologies are being investigated. Multi-band optical networks have raised as a very interesting candidate due to the potential increased capacity they offer thanks to the exploitation of multiple bands of the optical spectrum. Considering the whole telecom ecosystem, multi-band optical networks will coexist with other technological segments (e.g., Radio Access Network (RAN)) with the aim of provisioning services across the end-to-end infrastructure. With the advent of 5G and beyond 5G (B5G) architectures, novel provisioning paradigms are taking preponderance, such as the case of network slicing, which represents a radical paradigm change with respect to legacy business and provisioning models. As such, proper solutions for supporting network slice provisioning and runtime maintenance at the data plane are required. With this in mind, in this paper we present a control and orchestration architecture for the configuration and maintenance of network slices in multi-band optical networks, in support of B5G end-to-end services. Indeed, quality assurance and maintenance at all levels is seen as a cornerstone in B5G architectures. Thus, proper mechanisms adapted to the nature of the underlying sliceable multi-band data plane are required to ensure the quality of deployed slices. In this regard, we also present a novel band-adaptive protection scheme which takes advantage of the properties of the multi-band data plane so as to enhance the robustness of slices against quality degradations. We showcase the provisioning and maintenance of multi-band optical network slices by means of an experimental demonstration in a real testbed deployed at our premises. In addition, we evaluate the performance of the proposed band-adaptive protection scheme for slice quality assurance in front of other strategies by means of extensive simulation analysis in larger network scenarios., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Evaluating the impact of the guard band width on the benefits of probabilistic constellation shaping in future flex-grid over multicore fibre optical backbone networks

  • Perelló Muntan, Jordi
  • Gené Bernaus, Joan M.
  • Cho, Junho
  • Spadaro, Salvatore
Probabilistic constellation shaping (PCS) has emerged as an advanced modulation technique that provides a fine-grained software-defined trade-off between achievable spectral efficiency (SE) and transmission reach to deliver optimal channel capacity at any distance. This paper quantifies the network throughput benefits resulting from adopting PCS in future Flex-Grid over multicore fibre optical backbone networks, compared to using traditional uniform modulation formats. In particular, different inter-channel guard band width configurations are accounted in our study, aiming to set guidelines on the technological requirements imposed to network spectrum selective switches (SSS) to take full PCS advantage in future optical backbone networks., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Autonomous resource assignment for optimal utilization in optical data centre infrastructures

  • Pagès Cruz, Albert
  • Biosca Caro, Jordi
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
We present an architectural solution based on data analytics for self-organizing optical data centers. Thanks to a reinforcement learning-based cognitive layer, an adaptive and autonomous resource assignment to deployed services is achieved., This work has been supported by the Spanish Government through project TRAINER-B (PID2020‐118011GB‐C22) with FEDER contribution., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Probabilistic constellation shaping in flex-grid over multicore fibre optical backbone networks: an energy savings evaluation

  • Perelló Muntan, Jordi
  • Gené Bernaus, Joan M.
  • Cho, Junho
  • Spadaro, Salvatore
Probabilistic constellation shaping (PCS) has been shown to close the gap to channel capacity at any distance, by providing a fine-grained software-defined trade-off between achievable spectral efficiency and transmission reach. Previous works on PCS performance evaluation in Flex-Grid over multicore fibre optical backbone networks have already noted its superior performance when compared to traditional modulation formats, as well as its potential to lower associated network capital expenditures (CAPEX) by allowing, for example, a reduction in the required number of transceivers to handle the offered traffic demands. This paper investigates the potential of PCS to lower network energy consumption, as a way to contribute to the eco-friendliness and sustainability of next-generation optical backbone networks. © 2024 IEEE., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Evaluation of probabilistic constellation shaping performance in Flex Grid over multicore fiber dynamic optical backbone networks [Invited]

  • Perelló Muntan, Jordi
  • Gené Bernaus, Joan M.
  • Spadaro, Salvatore
In this paper, we present a worst-case methodology for estimating the attainable spectral efficiency over end-to-end paths across a Flex Grid over multicore fiber (MCF) optical network. This methodology accounts for physical link noise, as well as for the signal-to-noise ratio in the Add module (SNR TX ) of spatial-division-multiplexing-enabled reconfigurable optical add and drop multiplexers (SDM-ROADMs), introducing a dominant noise contribution over that of their Bypass and Drop modules. The proposed methodology is subsequently used to quantify the benefits that probabilistic constellation shaping (PCS) can bring to Flex-Grid/MCF dynamic optical backbone networks, compared to using traditional polarization-multiplexed modulation formats. In a first step, insight is provided into the spectral efficiency attainable along the precomputed end-to-end paths in two reference backbone networks, either using PCS or traditional modulation formats. Moreover, in each one of these networks, two SNR TX values are identified: the SNR TX yielding the maximum average paths’ spectral efficiency, as well as an SNR TX that, although slightly degrading the average paths’ spectral efficiency (by 10%), would yet enable a cost-effective SDM-ROADM Add module implementation. Extensive simulations are conducted to analyze PCS offered load gains under 1% bandwidth blocking probability. Furthermore, the study lastly focuses on finding out whether lower fragmentation levels in Flex-Grid/MCF dynamic optical backbone networks can push PCS benefits even further., Funding: Agencia Estatal de Investigación (PID2020-118011GB-C21, PID2020-118011GB-C22, RED2018-102585-T)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Demonstration of a control plane in support of E2E deterministic service provisioning over a multidomain multi-technology 6G network

  • Agraz Bujan, Fernando
  • Pagès Cruz, Albert
  • Calvillo Fernández, Alejandro
  • Rico Menendez, David
  • De La Oliva Delgado, Antonio
  • Giardina, Pietro G.
  • Ravalli, Matteo
  • Carcel Cervera, José Luis
  • Ruiz Ramírez, Marc
  • Velasco Esteban, Luis Domingo
  • Spadaro, Salvatore
The use cases associated to the emerging 6G technology demand a dynamic and adaptive network operation capable of addressing the specific requirements of heterogeneous data plane technologies. This demonstration presents the operation of a multi-domain multi-technology control plane architecture designed to provision end-to-end (E2E) connectivity with deterministic performance guarantees. Key innovations highlighted in the demonstration include homogenized configuration of diverse data plane technologies, advanced topology abstraction enabling Key Performance Indicator (KPI)-aware path computation, and the use of digital twin (DT)-based KPI estimation to support deterministic connectivity configuration. These capabilities collectively showcase a promising approach for managing the complexity and performance demands of future 6G networks., This publication is supported by the European Commission through Grant No. 101095890 (Predict-6G project) and the project TRAINER-B (PID2020-118011GBC22) funded by MCIN/AEI/10.13039/ 501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Low-cost all-optical switching nodes for ultra-dense optical metro-access networks

  • Sarmiento Hernández, Samael
  • Lázaro Villa, José Antonio
Optical metro-access networks (OMANs) must enable the connectivity among 5G-based radio stations, edge datacentres, businesses, and home users. In such a heterogenous scenario, greater scalability, higher levels of dynamic connectivity and flexibility, reduced end-to-end latency, and increased energy efficiency are required. Mesh-based ultra-dense wavelength division multiplexing (u-DWDM) OMANs using reconfigurable optical switching nodes are a promising solution. However, the designs of traditional optical switching nodes relay on wavelength-selective switches (WSSs), which provide high network reconfigurability only at a high cost, making them prohibitive for OMANs. Moving away from this design approach, we proposed a novel low-cost and energy-efficient design based on a modular DWDM structure for reconfigurable optical add-drop multiplexer (ROADM) and optical cross-connects (OXC) nodes compatible with mesh-based u-DWDM OMANs. Results show that proposed solutions can provide performance close to that of WSS-based OXCs but with a switching node cost reduction of one order magnitude., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

KPI-aware service provisioning for remote industrial control systems management

  • Pagès Cruz, Albert
  • Guasch Mesià, Enric
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
The advent of B5G/6G communication infrastructures answers to the requirements posed by emerging use cases and business models, such as Industry 4.0 and autonomous guided vehicles, which impose a set of highly demanding Key Performance Indicators (KPIs). In this regard, time-engineered applications are of particular importance. Said applications, while do not may impose very demanding latencies, they impose a strict control over them to ensure a deterministic service performance. This has given rise to the concept of Deterministic Networking that relies on adding deterministic capabilities to all involved network infrastructures. In general, optical networks are seen as one of the main enablers of latency and jitter-bounded communications, due to their intrinsic deterministic nature. In the framework of Industry 4.0 use cases, such capability can be exploited to enable remote control of optically interconnected smart factories, contributing this way to reduce both CAPEX and OPEX. However, the estimation of KPIs across optically interconnected smart factories/client domains and the provisioning of end-to-end (E2E) services arises several challenges. In this work, we present firstly multiple service provisioning schemas (single-vs multi-path) leveraging the capabilities of the Software Defined Networking (SDN) paradigm. Then, we provide tools and algorithms for best-case KPI estimation and resource allocation decision and analyze the impact of supporting heterogeneous KPIs into the obtained overall network performance., This publication is supported by the project TRAINER-B (PID2020- 118011 GB-C22) funded by MCIN/AEI/10.13039/501100011033 and the by the European Commission through Grant No. 101095890 (Predict-6G project)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

On the benefits of optical disaggregated datacentre infrastructures for machine learning applications

  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
ML applications present time varying requirements that should be accounted for an optimized deployment. We evaluate the benefits of disaggregated DC infrastructures for supporting them and propose a dynamic re-orchestration strategy for improved resource usage., This publication is supported by the project TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Reducing the number of transceivers with probabilistic constellation shaping in flex-grid over MCF optical backbone networks

  • Perelló Muntan, Jordi
  • Gené Bernaus, Joan M.
  • Cho, Junho
  • Spadaro, Salvatore
This paper quantifies the potential reduction in the number of required transceivers that the use of probabilistic constellation shaping (PCS) can bring to Flex-Grid over multicore fiber (MCF) optical backbone networks, which can directly lead to a reduction in network capital expenditure (CAPEX). Results from two different backbone networks illustrate that PCS can significantly decrease the number of required transceivers compared to using traditional modulation formats, thanks to the finer granularity in spectral efficiency. The observed reduction becomes more prominent (up to 22.3%) as the traffic profile bit-rates and the network physical distances increase., This publication is part of the Spanish I+D+i projects TRAINER-A and TRAINER-B (refs. PID2020-118011GB-C21 and PID2020-118011GB-C22), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

On the complexity of configuration and orchestration for enabling disaggregated server provisioning in optical composable data centers

  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Spadaro, Salvatore
Due to the limitations of traditional data center (DC) architectures, the concept of infrastructure disaggregation has been proposed. DC resources are separated into multiple blades to be exploited independently. As a result, composable DC (CDC) infrastructures are achieved, enhancing the modularity of resource provisioning. However, disaggregation introduces additional challenges that need to be carefully analyzed. One relates to the potential complexity increase on the orchestration and infrastructure configuration that need to be performed when provisioning resources to support services. This aspect is highly influenced by the distribution of resources at the physical infrastructure. As such, when analyzing the performance of a CDC, it becomes essential to also study the related operational complexity of the resource orchestration and configuration phases. Furthermore, the requirements of several tenant services may impose heterogeneous deployments over the shared physical infrastructure in the form of either disaggregated single-server or multi-server distributions. The associated orchestration/configuration cost is again highly influenced by the data plane architecture of the CDC. With these aspects in mind, in this paper, we provide a methodology for analysis of the complexity of resource orchestration for a service deployment and the associated configuration cost in optical CDCs, considering various service deployment setups. A selected set of CDC architectures found in the literature is employed to quantitatively illustrate how the data plane design and service deployment strategies affect the complexity of infrastructure configuration and resource orchestration., This work has been supported by the Spanish Government through project TRAINER-B (PID2020-118011GB-C22) with FEDER contribution., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Open-source 5G digital twin: Virtualizing core and RAN for network replication

  • Rodrigues Dos Santos, Cristhian Jose
  • Mateos Pérez, Izan
  • Lázaro Villa, José Antonio
  • Anguera Lo, Joan
  • Umbert Juliana, Anna
This paper presents a proposed methodology for creating digital twins of 5G networks using open-source 5G core and Radio Access Network (RAN) implementations. Our research will demonstrate how virtualized network functions can be deployed to create accurate digital replicas of operational 5G infrastructures. We will evaluate three leading open-source 5G core implementations—Open5GS, free5GC, and OpenAir-Interface—assessing their performance characteristics and suitability for digital twin applications. The proposed architecture will specifically replicate a distributed multi-campus research network, featuring multiple gNodeB units at each location connected through IP transport networks to Compact Mobility Units (CMUs) that bundle core network functions. Our implementation will enable bi-directional synchronization between physical networks and their digital counterparts, facilitating testing, optimization, and AI/ML model training without disrupting operational environments. Performance benchmarks and implementation guidelines provided in this paper will contribute to the growing field of network digital twins, offering a cost-effective approach for creating high-fidelity network replicas using open-source tools., This work has been partially financed by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation program Grant Agreement No. 101139182, 6GEWOC, and Spanish MICIU founded, TRAINER-B (PID2020-118011GBC22) and MTDFP project ELEGANT (TSI-064100-2023-0009)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

6G-EWOC: Crowdsourced SLAM data fusion for safe and efficient ADAS driving

  • Lázaro Villa, José Antonio
  • Casas Pla, Josep Ramon
  • Ruiz Hidalgo, Javier
  • Cortada Garcia, Martí
  • Martin Pey, Gerard
  • Salavedra Pujol, Judit
  • Wang, Mingrui
  • Theodoropoulou, Eleni
  • Lyberopoulos, George
  • Garcia Gómez, Pablo
  • Royo Royo, Santiago
  • Riu Gras, Jordi
  • Marcus, Carina
  • Eriksson, Olof
  • Schrenk, Bernhard
  • Fàbrega Sánchez, Josep Maria
The development of transport infrastructures for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles operating efficiently and safely in congestion-free traffic flows is a major challenge for telecommunications technologies. Simultaneous Localization and Mapping (SLAM) plays a crucial role in ensuring uninterrupted journeys for emergency vehicles and increasing the safety of vulnerable road users in complex traffic scenarios. Accurate SLAM mapping for ADAS systems requires data from different sensor technologies –such as high-resolution cameras or Radio/Light Detection and Ranging (RaDAR/LiDAR)– to be effectively combined or fused. Sensor fusion results in high data throughput and low latency requirements. However, optimal mapping outcomes occur when processing systems fuse data from sensors positioned at diverse locations within the traffic scene. By crowdsourcing diverse sensors, we can multiply the view angles, mitigate occlusions and improve the overall scene coverage. Yet, this approach introduces additional challenges for communication systems within both the vehicles and the infrastructure. Addressing these challenges is essential for seamless development of safe and efficient ADAS driving techniques., This work has received funding from the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation Programme under Grant Agreement No. 101139182, and Spanish MICIU founded, TRAINER-B (PID2020-118011GB-C22)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Data plane technology-agnostic control and orchestration architecture for optical disaggregated data centers

  • Agraz Bujan, Fernando
  • Pagès Cruz, Albert
  • Spadaro, Salvatore
We propose a novel SDN control and orchestration architecture to provide composed IaaS over optical disaggregated data centers. We experimentally validate intent-based mechanisms that make the architecture independent from the underlying physical infrastructure technology., This publication is part of the Spanish I+D+i project TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Optical phased array antenna apodization for lidar in autonomous vehicles

  • Lozano, José
  • Jiménez, Humberto
  • Torres Benito, Sergio
  • Biosca Marrón, Pau
  • Fontanet Albinyana, Bernat
  • Pinazo Donoso, Jorge
  • Lerín, Adolfo
  • Dios Otín, Víctor Federico
  • Casas Pla, Josep Ramon
  • Lázaro Villa, José Antonio
This paper presents the specific design of an Optical Phased Array antenna (OPA) to apodize the emission of a lidar in the context of a project where diverse optoelectronic sensors such as cameras, radars, and commercial lidars are used to provide data in order to fuse them and develop perception for robots as future autonomous vehicles. While mechanical based lidars are already commercially available, this work focuses on designing much more robust and potentially cheaper lidars based on photonic integrated circuits and energy optimization through the apodization of the emission of the OPA., This publication is part of the Spanish I+D+i project: PTAS-20211011, “Percepción Inteligente para los Vehículos Autónomos y Conectados”, INPERCEPT, funded by CDTI/MCIN and TRAINER-B (ref. PID2020-118011GB-C22), funded by MCIN/ AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

On the selection of KPI-aware E2E paths for deterministic services in 6G networks

  • Spadaro, Salvatore
  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
  • Blanco Caamaño, Marta
  • Contreras, Luis Miguel
In the 6G ecosystem, the provisioning of deterministic services with KPI guarantees over multi-technological network domains requires the proper selection of the end-to-end (E2E) paths. Since each technological domain has its own capabilities and resources, in an E2E perspective, the proper selection of the domains to achieve the service KPIs is fundamental. The paper discusses the challenges of the E2E path/domain selection, provides an overall supporting control plane architecture and presents a proof of concept., This publication is supported by the projects TRAINER-B (PID2020-118011GB-C22) funded by MCIN/AEI/10.13039/ 501100011033 and by the European Commission through Grant No. 101095890 (Predict-6G project)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Machine learning-based actuation orchestration for inter-/intra-data center networks

  • Spadaro, Salvatore
  • Pagès Cruz, Albert
  • Agraz Bujan, Fernando
Datacenter (DC) infrastructures are essential to support the requirements posed by nowadays digital society and emerging industrial trends. In such context, a proper actuation management has become especially relevant for service quality assurance operations. In situations where it may be difficult to determine which is the sub-system that needs to apply an actuation, machine learning (ML)-based strategies become valuable assets to orchestrate the actuations to be applied. In this paper, we discuss three strategies for actuation orchestration in inter-/intra-DC scenarios interconnected through optical network systems and benchmark them in terms of requirements that they impose and the achieved performance, Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Phase noise reduction in continuous-variable quantum key distribution using digital filtering

  • Sarmiento, Samael
  • Llanos Pla, Elisabeth
  • Adillon Albero, Pol
  • Tabares Giraldo, Jeison
  • Lázaro Villa, José Antonio
  • Etcheverry, Sebastian
Quantum key distribution (QKD) enables information-theoretic-secure secret key exchange thanks to the laws of quantum mechanics. Since it can easily be incorporated into existing telecom networks, continuous-variable QKD (CV QKD) using coherent states and coherent detection has recently emerged as a promising candidate. However, the secret key rate and link distance in CV QKD systems are still limited by the imperfections of used components. In this work, through simulations, we study the use of different digital filtering techniques for optical phase recovery, aided by pilot symbols, to mitigate the phase noise induced by the coherent mixing of two free-running lasers in a CV QKD system. Moving average, Butterworth and unscented Kalman filters are evaluated for different phase drift conditions. Results show that phase recovery from small amplitude pilot symbols, along with further digital filtering, can considerably reduce phase noise and measurement error, while increasing the secret key rate and link distance of the CV QKD system., This work was supported in part by the European Union through the Digital Europe Work Programme 2021-2022 [DIGITAL-2021-QCI-01- INDUSTRIAL/QuarterProject/101091588], Spanish Ministry Grants PTQ2021-012121, PTQ2021-012123 and TRAINER-B (PID2020- 118011GB-C22), funded by [MCIN/AEI/10.13039/ 50110001103], as well as Pla de Doctorats Industrials del Departament de Recerca i Universitats de la Generalitat de Catalunya under Grants 2022-DI-0118 and 2023-DI-0052., Peer Reviewed, Postprint (published version)