Search

Optical point-to-multipoint (P2MP) connectivity based on digital subcarrier multiplexing (DSCM) has been shown as a solution for the metro-access segment that is able to reduce capital and operational costs and support the capacity and high dynamicity needs of future 6G services. To achieve maximum performance, activation and deactivation of subcarriers must be done near-real-time to provide just the capacity needed to support the input traffic. In this paper, we investigate the applicability of various approaches capable of supporting the near-real-time operation requirement. Starting from the centralized approach that can be carried out on the centralized software-defined networking (SDN) controller, we also explore distributed approaches that might relieve the SDN controller from near-real-time operation. In particular, we explore the performance of deploying a multiagent system (MAS), where intelligent agents run on top of the nodes in the P2MP tree and communicate among them. Illustrative results show that the distributed approaches can achieve a performance close to that of the centralized one, while reducing communication needs. Results also show the importance of traffic/capacity prediction to anticipate the activation of subcarriers., The research leading to these results has received funding from the Smart Networks and Services Joint Undertaking under the European Union's Horizon Europe research and innovation programme under Grant Agreement No. 101096120 (SEASON), the MICINN IBON (PID2020-114135RB-I00) project and from the ICREA Institution., Peer Reviewed, Postprint (author's final draft)

The deployment of beyond 5G and 6G network infrastructures will enable highly dynamic services requiring stringent Quality of Service (QoS). Supporting such combinations in today’s transport networks will require high flexibility and automation to operate near real-time and reduce overprovisioning. Many solutions for autonomous network operation based on Machine Learning require a global network view, and thus need to be deployed at the Software-Defined Networking (SDN) controller. In consequence, these solutions require implementing control loops, where algorithms running in the controller use telemetry measurements collected at the data plane to make decisions that need to be applied at the data plane. Such control loops fit well for provisioning and failure management purposes, but not for near real-time operation because of their long response times. In this paper, we propose a distributed approach for autonomous near-real-time flow routing with QoS assurance. Our solution brings intelligence closer to the data plane to reduce response times; it is based on the combined application of Deep Reinforcement Learning (DRL) and Multi-Agent Systems (MAS) to create a distributed collaborative network control plane. Node agents ensure QoS of traffic flows, specifically end-to-end delay, while minimizing routing costs by making distributed routing decisions. Algorithms in the centralized network controller provide the agents with the set of routes that can be used for each traffic flow and give freedom to the agents to use them during operation. Results show that the proposed solution is able to ensure end-to-end delay under the desired maximum and greatly reduce routing costs. This performance is achieved in dynamic scenarios without previous knowledge of the traffic profile or the background traffic, for single domain and multidomain networks., The research leading to these results has received funding from the European Commission thought the HORIZON SNS JU DESIRE6G (G.A. 101096466), the MINECO UNICO5G TIMING (TSI-063000-2021-145) and the MICINN IBON (PID2020-114135RB-I00) projects, and from the ICREA Institution., Peer Reviewed, Postprint (author's final draft)

The Intent-Based Networking (IBN) paradigm targets at defining high-level abstractions, so network operators can define what are their desired outcomes without specifying how they would be achieved. The latter can be achieved by leveraging network programmability, monitoring and data analytics, as well as the key assurance component. In this paper, we introduce the IBN paradigm and its application to optical networking, highlighting the benefits that Machine Learning (ML) algorithms can provide to IBN. Illustrative examples of intent-based operation are presented for proactive self-configuration and cooperative intent operation., The research leading to these results has received funding from the H2020 B5G-OPEN (G.A. 101016663) and the AEI IBON (PID2020-114135RB-I00) projects and from the ICREA institution., Peer Reviewed, Postprint (author's final draft)

We exploit the intrinsic advantages of a time and frequency domain digital twin to detect degradations and to estimate their severity. Noticeable performance shown for filter failures confirms the usefulness of this approach., The research leading to these results has received funding from the European Community through the MSCA MENTOR (G.A. 956713) and the H2020 B5G-OPEN (G.A. 101016663) projects, the AEI through the IBON (PID2020-114135RB-I00) project, and by the ICREA institution, Peer Reviewed, Postprint (author's final draft)

Telemetry data and big data share volume, velocity, variety, veracity and value characteristics. We propose a distributed telemetry architecture and show how intelligence can help dealing with the 5 V’s of optical networks telemetry data., The research leading to these results has received funding from the HORIZON SEASON (G.A. 101096120) and the MICINN IBON (PID2020-114135RB-I00) projects and from the ICREA Institution., Peer Reviewed, Postprint (author's final draft)

New 5G and beyond applications demand strict delay requirements. In this paper, we propose coordination between radio access and optical transport to guarantee such delay while optimizing optical capacity allocation. Illustrative results show near real-time autonomous capacity adaptation benefits based on radio access delay requirements., The research leading to these results has received funding from the HORIZON SEASON (G.A. 101096120), the UNICO5G TIMING (TSI-063000-2021-145), and the MICINN IBON (PID2020-114135RB-I00) projects and from the ICREA institution., Peer Reviewed, Postprint (author's final draft)

As the dynamicity of the traffic increases, the need for self-network operation becomes more evident. One of the solutions that might bring cost savings to network operators, is that of the dynamic capacity management of large packet flows, especially in the context of packet over optical networks. Machine Learning, and particularly Reinforcement Learning (RL), seem to be an enabler for autonomicity, as a result of its inherent capacity to learn from experience. In this tutorial, we introduce RL and review its application for autonomous capacity management of traffic flows., This project has received funding from the Smart Networks and Services Joint Undertaking under the European Union's Horizon Europe research and innovation programme under Grant Agreement No. 101096120 (SEASON), from the MICINN IBON (PID2020-114135RB-I00) project and from the ICREA Institution., Peer Reviewed, Postprint (author's final draft)

The development of Digital Twins to represent the optical transport network might enable multiple applications for network operation, including automation and fault management. In this work, we use GNPy as a Signal to Noise Ratio (SNR) digital twin of the optical network for failure management applications. The methodology proposed for failure management consists in comparing the QoT measured in the transponders with the one estimated using the digital twin and try to explain detected deviations as changes in the value of input parameters of the Quality of Transmission (QoT) model representing the optical devices, like noise figure (NF) in optical amplifiers (OA) and reduced Optical SNR in the Wavelength Selective Switches (WSS). By applying reverse engineering, the value of those modeling parameters can be estimated as a function of the observed QoT of the lightpaths. Experiments reveal high accuracy estimation of modeling parameters, and results obtained by simulation show large anticipation of soft-failure detection and localization, as well as accurate identification of degradations before they have a major impact on the network., The research leading to these results has received funding from the H2020 B5G-OPEN (G.A. 101016663) and the AEI IBON (PID2020-114135RB-I00) projects and from the ICREA institution., Peer Reviewed, Postprint (author's final draft)

A DRL approach with a specific reward function is proposed for autonomous flow routing operating on multilayer scenarios. Illustrative results reveal that the DRL achieves optimal flow routing in terms of cost and service quality. © 2022 IEICE., The research leading to these results has received funding from the H2020 B5G-OPEN (G.A. 101016663), the MINECO-NextGenerationEU TIMING (TSI-063000-2021-145), the MICINN IBON (PID2020-114135RB-I00), and the ICREA Institution., Peer Reviewed, Postprint (published version)

This Ph.D. thesis focuses on the reliable autonomous operation of multilayer optical networks. The first objective focuses on the reliability of the optical network and proposes methods for health analysis related to Quality of Transmission (QoT) degradation. Such degradation is produced by soft-failures in optical devices and fibers in core and metro segments of the operators’ transport networks. Here, we compare estimated and measured QoT in the optical transponder by using a QoT tool based on GNPy. We show that the changes in the values of input parameters of the QoT model representing optical devices can explain the deviations and degradation in performance of such devices. We use reverse engineering to estimate the value of those parameters that explain the observed QoT. We show by simulation a large anticipation in soft-failure detection, localization and identification of degradation before affecting the network. Finally, for validating our approach, we experimentally observe the high accuracy in the estimation of the modeling parameters. The second objective focuses on multilayer optical networks, where lightpaths are used to connect packet nodes thus creating virtual links (vLink). Specifically, we study how lightpaths can be managed to provide enough capacity to the packet layer without detrimental effects in their Quality of Service (QoS), like added delays or packet losses, and at the same time minimize energy consumption. Such management must be as autonomous as possible to minimize human intervention. We study the autonomous operation of optical connections based on digital subcarrier multiplexing (DSCM). We propose several solutions for the autonomous operation of DSCM systems. In particular, the combination of two modules running in the optical node and in the optical transponder activate and deactivate subcarriers to adapt the capacity of the optical connection to the upper layer packet traffic. The module running in the optical node is part of our, Esta tesis doctoral se centra en la operación autónoma y confiable de redes ópticas multicapa. El primer objetivo se centra en la fiabilidad de la red óptica y propone métodos para el análisis del estado relacionados con la degradación de la calidad de la transmisión (QoT). Dicha degradación se produce por fallos en dispositivos ópticos y fibras en las redes de transporte de los operadores que no causan el corte de la señal. Comparamos el QoT estimado y medido en el transpondedor óptico mediante el uso de una herramienta de QoT basada en GNPy. Mostramos que los cambios en los valores de los parámetros de entrada del modelo QoT que representan los dispositivos ópticos pueden explicar las desviaciones y la degradación en el rendimiento de dichos dispositivos. Usamos ingeniería inversa para estimar el valor de aquellos parámetros que explican el QoT observado. Mostramos, mediante simulación, una gran anticipación en la detección, localización e identificación de fallas leves antes de afectar la red. Finalmente, validamos nuestro método de forma experimental y comprobamos la alta precisión en la estimación de los parámetros de los modelos. El segundo objetivo se centra en las redes ópticas multicapa, donde se utilizan conexiones ópticas (lightpaths) para conectar nodos de paquetes creando así enlaces virtuales (vLink). Específicamente, estudiamos cómo se pueden gestionar los lightpaths para proporcionar suficiente capacidad a la capa de paquetes sin efectos perjudiciales en su calidad de servicio (QoS), como retrasos adicionales o pérdidas de paquetes, y al mismo tiempo minimizar el consumo de energía. Estudiamos el funcionamiento autónomo de conexiones ópticas basadas en multiplexación de subportadoras digitales (DSCM) y proponemos soluciones para su funcionamiento autónomo. En particular, la combinación de dos módulos que se ejecutan en el nodo óptico y en el transpondedor óptico activan y desactivan subportadoras para adaptar la capacidad de la conexión óptica al trá, Postprint (published version)

The intent-based networking (IBN) paradigm targets defining high-level abstractions so network operators can define what their desired outcomes are without specifying how they would be achieved. The latter can be achieved by leveraging network programmability, monitoring, and data analytics, as well as the key assurance component. In this tutorial, we introduce the IBN paradigm and its application to optical networking, highlighting the benefits that machine learning (ML) algorithms can provide to IBN. Because the deployment of ML applications requires a specific orchestrator to create ML functions that are connected as ML pipelines, we show an implementation of such an orchestrator. Some challenges and solutions are presented for the generation of accurate synthetic data, proactive self-configuration, and cooperative intent operation. Illustrative examples of intent-based operation and numerical results are presented, and the obtained performance is discussed., The research leading to these results has received funding from the MICINN IBON (PID2020-114135RB-I00) project and from the ICREA Institution., Peer Reviewed, Postprint (author's final draft)

A combined LSTM and RL approach is proposed for dynamic connection capacity allocation. The LSTM predictor anticipates periodical long-term sharp traffic changes and extends short-term RL knowledge. Numerical results show remarkable performance., The research leading to these results has received funding from the Spanish MINECO TWINS project (TEC2017-90097-R) and by the ICREA institution., Peer Reviewed, Postprint (published version)

The performance of optical devices can degrade because of aging and external causes like, for example, temperature variations. Such degradation might start with a low impact on the Quality of Transmission (QoT) of the supported lightpaths (soft-failure). However, it can degenerate into a hard-failure if the device itself is not repaired or replaced, or if an external cause responsible for the degradation is not properly addressed. In this work, we propose comparing the QoT measured in the transponders with the one estimated using a QoT tool. Those deviations can be explained by changes in the value of input parameters of the QoT model representing the optical devices, like noise figure in optical amplifiers and reduced Optical Signal to Noise Ratio in the Wavelength Selective Switches. By applying reverse engineering, the value of those modeling parameters can be estimated as a function of the observed QoT of the lightpaths. Experiments reveal high accuracy estimation of modeling parameters, and results obtained by simulation show large anticipation of soft-failure detection and localization, as well as accurate identification of degradations before they have a major impact on the network., The research leading to these results has received funding from the AEI/FEDER through the TWINS project (TEC2017-90097-R) and from the ICREA institution., Peer Reviewed, Postprint (author's final draft)

As the dynamicity of the traffic increases, the need for self-network operation becomes more evident. One of the solutions that might bring cost savings to network operators is the dynamic capacity management of large packet flows, especially in the context of packet over optical networks. Machine Learning, particularly Reinforcement Learning, seems to be an enabler for autonomicity as a result of its inherent capacity to learn from experience. However, precisely because of that, RL methods might not be able to provide the required performance (e.g., delay, packet loss, and capacity overprovisioning) when managing the capacity of packet flows, until they learn the optimal policy. In view of that, we propose a management lifecycle with three phases: (i) a self-tuned threshold-based approach operating just after the packet flow is set up and until enough data on the traffic characteristics are available; (ii) an RL operation based on models pre-trained with a generic traffic profile; and (iii) an RL operation with models trained for real traffic. Exhaustive simulation results confirm the poor performance of RL algorithms until the optimal policy is learnt and when traffic characteristics change over time, which prevents deploying such methods in operators’ networks. In contrast, the proposed lifecycle outperforms benchmarking approaches, achieving noticeable performance from the beginning of operation while showing robustness against traffic changes., This research received funding from the European Community through the B5G-OPEN project (101016663), from the AEI IBON project (PID2020-114135RB-I00), and from the ICREA Institution., Peer Reviewed, Postprint (published version)

A RL agent trained offline for reliability and able to refine its policies during online operation is proposed. Results for three illustrative flow automation use cases show remarkable performance with extraordinary adaptability to changes., The research leading to these results has received funding from the Spanish MINECO TWINS project (TEC2017-90097-R) and by the ICREA institution., Peer Reviewed, Postprint (published version)

The massive deployment of 5G and beyond will require high capacity and low latency connectivity services, so network operators will have either to overprovision capacity in their transport networks or to upgrade the optical network controllers to make decisions nearly in real time; both solutions entail high capital and operational expenditures. A different approach could be to move the decision making toward the nodes and subsystems, so they can adapt dynamically the capacity to the actual needs and thus reduce operational costs in terms of energy consumption. To achieve this, several technological challenges need to be addressed. In this paper, we focus on the autonomous operation of Digital Subcarrier Multiplexing (DSCM) systems, which enable the transmission of multiple and independent subcarriers (SC). Herein, we present several solutions enabling the autonomous DSCM operation, including: i) SC quality of transmission estimation; ii) autonomous SC operation at the transmitter side and blind SC configuration recognition at the receiver side; and iii) intent-based capacity management implemented through Reinforcement Learning. We provide useful guidelines for the application of autonomous SC management supported by the extensive results presented., The research leading to these results has received funding from the European Community's through the MSCA REAL-NET project (G.A. 813144), by the AEI/FEDER through the TWINS project (TEC2017-90097-R), and by the ICREA institution., Peer Reviewed, Postprint (author's final draft)

We propose an Intent-Based Networking solution based on Reinforcement Learning (RL). RL-based intents with specific operational objectives and coordinated operation between network layers are developed. Results show service assurance with automatic adaptation to changing traffic., The research leading to these results has received funding from the EC through the Spanish MINECO TWINS project (TEC2017-90097-R) and from ICREA., Peer Reviewed, Postprint (author's final draft)

© 2020 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 optical networks, degradation of the Quality of Transmission (QoT) can be the outcome of soft-failures in optical devices, like Optical Transponders, Wavelength Selective Switches (WSS) and Optical Amplifiers (OA). In this paper, we assume time-dependent degradations on ROADMs and OAs. Specifically, several degradations are considered: i) the noise figure can increase linearly over time due to the aging of the components; ii) the maximum of optical output power of the amplifiers can decrease because of the degradation in the pump lasers of the EDFAs; iii) aging effects, e.g., due to fiber splices; and iv) the OSNR can vary caused by frequency drift of WSSs due to temperature variations. Our proposal for degradation detection and soft-failure localization includes algorithms that are able to detect and localize the degradation in early stages and facilitate network diagnosis.In addition, we propose an architecture where the control plane consist of a network controller, a Monitoring and Data Analytics system and a QoT tool based on GNPy that are interconnected with each other., The research leading to these results has received funding from the Spanish MINECO TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (published version)

A soft-failure localization and key working parameters estimation system is proposed for network diagnosis and maintenance. We show that a double analysis of monitoring data and estimated working parameters greatly anticipates degradations, The research leading to these results has received funding from the EC through the METRO-HAUL project (G.A. nº 761727), from the Spanish MINECO TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA), Peer Reviewed, Postprint (published version)

© 2019 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 monitor the optical spectra of outgoing links, Optical Spectrum Analyzers (OSA) can deployed in the optical nodes acquiring the optical spectra of outgoing links and analyzing optical signals to detect those soft-failures that affect the shape of the spectrum, like Filter Shift and Filter Tightening. In this paper, we rely on the residual-based approach spectra analysis that uses a set of residual signals calculated by subtracting the measured signal by the OSA from an expected version of the signal. In this paper, we assume a network scenario, where nodes with optical filters of different characteristics (e.g., 2nd, 3rd, and 4th order Gaussian) are installed. In this scenario, the possibility of generating complete data set for machine learning training purposes that include every combination of filter and failure is difficult to achieve. Instead, we propose an adaptation mechanism that transform the expected effects of every filter type thus, emulating single filter-type networks. Exhaustive experiments are carried out to show the performance of the proposed adaptation under filter failures., This work was partially supported by the EC through the METRO-HAUL project (G.A. nº 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan ICREA Institution., Peer Reviewed, Postprint (author's final draft)