Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 52
Encontrada(s) 1 página(s)

Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Artículo científico (JournalArticle)

Deep-FDA: Using Functional Data Analysis and Neural Networks to Characterize Network Services Time Series

  • Perdices Burrero, Daniel
  • López de Vergara Méndez, Jorge Enrique
  • Ramos de Santiago, Francisco Javier
In network management, it is important to model baselines, trends, and regular behaviors to adequately deliver network services. However, their characterization is complex, so network operation and system alarming become a challenge. Several problems exist: Gaussian assumptions cannot be made, time series have different trends, and it is difficult to reduce their dimensionality. To overcome this situation, we propose Deep-FDA, a novel approach for network service modeling that combines functional data analysis (FDA) and neural networks. Specifically, we explore the use of functional clustering and functional depth measurements to characterize network services with time series generated from enriched flow records, showing how this method can detect different separated trends. Moreover, we augment this statistical approach with the use of autoencoder neural networks, improving the classification results. To evaluate and check the applicability of our proposal, we performed experiments with synthetic and real-world data, where we show graphically and numerically the performance of our method compared to other state-of-the-art alternatives. We also exemplify its application in different network management use cases. The results show that FDA and neural networks are complementary, as they can help each other to improve the drawbacks that both analysis methods have when are applied separately, This work has been partially supported by the European Commission under the project H2020 METRO-HAUL (Project ID: 761727), by the Spanish State Research Agency under the project AgileMon (AEI PID2019-104451RB-C21) and by the Spanish Ministry of Science, Innovation and Universities under the program for the training of university lecturers (Grant number: FPU19/05678)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Artículo científico (JournalArticle)

On the dynamics of valley times and its application to bulk-transfer scheduling

  • Muelas, David
  • García Dorado, José Luis
  • Albandea, Sergio
  • López de Vergara Méndez, Jorge Enrique
  • Aracil Rico, Javier
Periods of low load have been used for the scheduling of non-interactive tasks since the early stages of computing. Nowadays, the scheduling of bulk transfers—i.e., large-volume transfers without precise timing, such as database distribution, resources replication or backups—stands out among such tasks, given its direct effect on both the performance and billing of networks. Through visual inspection of traffic-demand curves of diverse points of presence (PoP), either a network, link, Internet service provider or Internet exchange point, it becomes apparent that low-use periods of bandwidth demands occur at early morning, showing a noticeable convex shape. Such observation led us to study and model the time when such demands reach their minimum, on what we have named valley time of a PoP, as an approximation to the ideal moment to carry out bulk transfers. After studying and modeling single-PoP scenarios both temporally and spatially seeking homogeneity in the phenomenon, as well as its extension to multi-PoP scenarios or paths—a meta-PoP constructed as the aggregation of several single PoPs—, we propose a final predictor system for the valley time. This tool works as an oracle for scheduling bulk transfers, with different versions according to time scales and the desired trade-off between precision and complexity. The evaluation of the system, named VTP, has proven its usefulness with errors below an hour on estimating the occurrence of valley times, as well as errors around 10% in terms of bandwidth between the prediction and actual valley traffic, This work has been partially supported by the European Commission under the project H2020 METRO-HAUL (Project ID: 761727)
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

SDN-enabled S-BVT for Disaggregated Networks: Design, Implementation and Cost Analysis

  • Nadal, Laia
  • Svaluto Moreolo, Michela
  • Hernández Gutiérrez, José Alberto
  • Fabrega, Josep M.
  • Casellas, Ramón
  • Muñoz, Raúl
  • Vilalta, Ricard
  • Rodríguez, Laura
  • Vílchez, F. Javier
Software-defined networking (SDN) and disaggregation are key technologies to fulfill the requirements of 5G and beyond optical metro networks. Indeed, open networking solutions will reduce vendor lock-in, achieving increased flexibility and programmability of the network. SDN-enabled sliceable bandwidth/bitrate variable transceivers (S-BVTs) are proposed to be adopted in metro networks in order to provide sustainable capacity growth and hyper-scalability, while enabling disaggregation and network flexibility/reconfigurability. We propose a transceiver modular approach following a pay-as-you grow model, which allows the S-BVT to be adapted to the traffic demand and network requirements. In fact, the S-BVT solution can be seen as a set of bandwidth/bitrate variable transceivers (BVTs) that can be pluggable and multi-vendor. Hence, SDN agents have been developed based on an OpenConfig vendor-neutral data model in order to efficiently reconfigure the S-BVTs fostering network agility and adaptability. Specifically, an optimized agent implementation is experimentally validated in order to increase the network efficiency and reduce the setup configuration time of an optical channel. Two slices/BVTs of 50 Gb/s each are successfully enabled and programmed to establish a high capacity flow of 100 Gb/s. The cost/power consumption of the proposed solution, based on direct detection (DD), is analyzed showing significant savings compared to 100 Gb/s coherent (CO) technology., This work was supported in part by the European Commission through the H2020-ICT-2016-2 METRO-HAUL Project under Grant G.A.761727 and in part by the Spanish Ministry MINECO Project AURORAS under Grant TEC RTI2018-99178-B-I00.
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

A techno-economic study of optical network disaggregation employing Open-Source Software business models for Metropolitan Area Networks

  • Hernández Gutiérrez, José Alberto
  • Quagliotti, Marco
  • Riccardi, Emilio
  • López, Víctor
  • González de Dios, Óscar
  • Casellas Regi, Ramón
This work provides a techno-economic evaluation of optical disaggregation architectures in the context of metropolitan area networks. The study compares two optical disaggregation options (partial vs. total) against the legacy benchmark where optical equipment is subject to vendor lock-in, as it is deployed in most networks today. We show that emerging open source software projects within the software-defined networking ecosystem can potentially yield significant cost savings for medium- and large-size network operators, while they can introduce extra flexibility and agility to network operations and service deployments., This work has been supported by EU H2020 project Metro-Haul, grant no. 761727 (https://metro-haul.eu).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Machine learning-based routing and wavelength assignment in software-defined optical networks

  • Martín Martínez, Ignacio
  • Troia, Sebastian
  • Hernández Gutiérrez, José Alberto
  • Rodríguez, Alberto
  • Musumeci, Francesco
  • Maier, Guido
  • Alvizu, Rodolfo
  • González de Dios, Óscar
Recently, machine learning (ML) has attracted the attention of both researchers and practitioners to address several issues in the optical networking field. This trend has been mainly driven by the huge amount of available data (i.e., signal quality indicators, network alarms, etc.) and to the large number of optimization parameters which feature current optical networks (such as, modulation format, lightpath routes, transport wavelength, etc.). In this paper, we leverage the techniques from the ML discipline to efficiently accomplish the routing and wavelength assignment (RWA) for an input traffic matrix in an optical WDM network. Numerical results show that near-optimal RWA can be obtained with our approach, while reducing computational time up to 93% in comparison to a traditional optimization approach based on integer linear programming. Moreover, to further demonstrate the effectiveness of our approach, we deployed the ML classifier into an ONOS-based software defined optical network laboratory testbed, where we evaluate the performance of the overall RWA process in terms of computational time., The authors would like to acknowl-edge the support of the project TEXEO (TEC2016-80339-R), funded by Spanish MINECO and the EU-H2020 Metrohaul project (grant no. 761727).
e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Artículo científico (JournalArticle)

Comprehensive model for technoeconomic studies of next-generation central offices for metro networks

  • Hernández Gutiérrez, José Alberto
  • Quagliotti, Marco
  • Serra, Laura
  • Luque, Lourdes
  • López Da Silva, Rafael
  • Rafel, Albert
  • Gonzalez De Dios, Oscar
  • López, Víctor
  • Eira, Antonio
  • Casellas, Ramón
  • Lord, Andrew
  • Pedro, Joao
  • Larrabeiti López, David
This paper introduces a novel and simplified cost model for designing and evaluating a Central Office Rearchitected as a Datacenter (CORD). The model includes equipment and elements for the realization of optical, packet switching, and data center parts with a special focus not only on relative costs but also on power consumption figures. The cost model is then applied to the design and comparison of a metropolitan area network (MAN) including both aggregation and metrocore nodes following several MAN node architectures based on CORD-like leaf-and-spine fabric. In particular, equipment disaggregation at the Central Offices, both on the packet-switching and optical components, can provide important cost savings to telco operators. On the other hand, incorporating computing/storage capabilities in the MAN for the realization of multiaccess edge computing (MEC) has a significant impact on the total network cost but especially on power consumption., This work has been supported by EU H2020 project Metro-Haul, grant no. 761727 (https://metro-haul.eu).
UVaDOC. Repositorio Documental de la Universidad de Valladolid
Publication Artículo científico (JournalArticle)

A Genetic Algorithm for VNF Provisioning in NFV-Enabled Cloud/MEC RAN Architectures

  • Ruiz Pérez, Lidia
  • Durán Barroso, Ramón José
  • Miguel Jiménez, Ignacio de
  • Khodashenas, Pouria S.
  • Pedreno Manresa, José Juan
  • Merayo Álvarez, Noemí
  • Aguado Manzano, Juan Carlos
  • Pavón Marino, Pablo
  • Siddiqui, Shuaib
  • Mata, Javier
  • Fernández Reguero, Patricia
  • Lorenzo Toledo, Rubén Mateo
  • Abril Domingo, Evaristo José
Producción Científica, 5G technologies promise to bring new network and service capacities and are expected to introduce significant architectural and service deployment transformations. The Cloud-Radio Access Networks (C-RAN) architecture, enabled by the combination of Software Defined Networking (SDN), Network Function Virtualization (NFV) and Mobile Edge Computing (MEC) technologies, play a key role in the development of 5G. In this context, this paper addresses the problems of Virtual Network Functions (VNF) provisioning (VNF-placement and service chain allocation) in a 5G network. In order to solve that problem, we propose a genetic algorithm that, considering both computing resources and optical network capacity, minimizes both the service blocking rate and CPU usage. In addition, we present an algorithm extension that adds a learning stage and evaluate the algorithm performance benefits in those scenarios where VNF allocations can be reconfigured. Results reveal and quantify the advantages of reconfiguring the VNF mapping depending on the current demands. Our methods outperform previous proposals in the literature, reducing the service blocking ratio while saving energy by reducing the number of active core CPUs., Ministerio de Economía, Industria y Competitividad (projects TEC2014-53071-C3-2-P, TEC2017-84423-C3-1-P and TEC2015-71932-REDT), Ministerio de Educación, Cultura y Deporte (projects BES-2015-074514 and FPU14/04227)
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

BER degradation detection and failure identification in elastic optical networks

  • Vela, Alba P.
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Fresi, Francesco
  • Sambo, Nicola
  • Cugini, Filippo
  • Meloni, Gianluca
  • Poti, Luca
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Castoldi, Piero
IEEE Optical connections support virtual links in MPLS-over-optical multilayer networks and therefore, errors in the optical layer impact on the quality of the services deployed on such networks. Monitoring the performance of the physical layer allows verifying the proper working of optical connections, as well as to detect bit error rate (BER) degradation and anticipate connection disruption. In addition, failure identification facilitates localizing the cause of the failure by providing a short list of potential failed elements and enables self-decision making to keep committed service level. In this paper, we analyze several failure causes affecting the quality of optical connections and propose two different algorithms: one focused on detecting significant BER changes in optical connections, named as BANDO, and the other focused on identify the most probable failure pattern, named as LUCIDA. BANDO runs inside the network nodes to accelerate degradation detection and sends a notification to the LUCIDA algorithm running on the centralized controller. Experimental measures were carried out on two different setups to obtain values for BER and received power and used to generate synthetic data used in subsequent simulations. Results show significant improvement anticipating maximum BER violation with small failure identification errors., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Real-time optical spectrum monitoring in filterless optical metro networks

  • Shariati, Mohammad Behnam
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Fresi, Francesco
  • Sgambelluri, Andrea
  • Cugini, Filippo
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
The final publication is available at Springer via http://dx.doi.org/10.1007/s11107-020-00890-z, Filterless optical networks (FONs) have been proposed as a feasible solution for optical metro networks. In addition, as a result of the shorter distance compared to core optical networks, direct detection optical transmission systems can be used in metro FONs, which reduces costs, as compared to coherent detection systems. In this work, we present two optical signal tracking approaches for FONs that allow to detect small frequency laser drift problems and enable safely reducing channel spacing. Additionally, we study the most proper resolution for optical spectrum analyzers continuously scanning the whole C-band. Proposed approaches are: (1) feature-based tracking and (2) residual-based tracking. Experiments are carried out to compare the performance of the approaches for both direct detection and coherent detection systems, in the case of a single optical signal with no neighboring signals nearby in the spectrum, as well as in the case of a group of optical signals closely allocated in the spectrum. The results show that the residual-based approach enriched with contextual information enables to better track and correct the wavelength drifts before they reach their limits (e.g.,¿±¿2.5 GHz), leading to the guard band reduction for what concerns wavelength drifts., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016-2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Demonstration of latency-aware 5G network slicing on optical metro networks

  • Shariati, Mohammad Behnam
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Pedreno Manresa, José Juan
  • Dochhan, Annika
  • Casellas Regi, Ramon
  • Siddique Muqaddas, Abubakar
  • González de Dios, Oscar
  • Luque Canto, L.
  • Lent, Bodo
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
The H2020 METRO-HAUL European project has architected a latency-aware, cost-effective, agile, and programmable optical metro network. This includes the design of semi-disaggregated metro nodes with compute and storage capabilities, which interface effectively with both 5G access and multi-Tbit/s elastic optical networks in the core. In this paper, we report the automated deployment of 5G services, in particular, a public safety video surveillance use case employing low-latency object detection and tracking using on-camera and on-the-edge analytics. The demonstration features flexible deployment of network slice instances, implemented in terms of ETSI NFV Network Services. We summarize the key findings in a detailed analysis of end-to-end quality of service, service setup time, and soft-failure detection time. The results show that the round-trip-time over an 80 km link is under 800 µs and the service deployment time under 180 seconds., Horizon 2020 Framework Programme (761727); Bundesministerium für Bildung und Forschung (16KIS0979K)., Peer Reviewed, Article signat per 25 autors/es: B. Shariati, Fraunhofer HHI, Berlin, Germany / L. Velasco, Universitat Politècnica de Catalunya, Barcelona, Spain / J.-J. Pedreno-Manresa, ADVA, Munich, Germany / A. Dochhan, ADVA, Munich, Germany / R. Casellas, Centre Tecnològic Telecomunicacions Catalunya, Castelldefels, Spain / A. Muqaddas, University of Bristol, Bristol, UK / O. Gonzalez de Dios, Telefónica, Madrid, Spain / L. Luque Canto, Telefónica, Madrid, Spain / B. Lent, Qognify GmbH, Bruchsal, Germany / J. E. Lopez de Vergara, Naudit HPCN, Madrid, Spain / S. Lopez-Buedo, Naudit HPCN, Madrid, Spain / F. Moreno, Universidad Politécnica de Cartagena, Cartagena, Spain / P. Pavon, Universidad Politécnica de Cartagena, Cartagena, Spain / M. Ruiz, Universitat Politècnica de Catalunya, Barcelona, Spain / S. K. Patri, ADVA, Munich, Germany / A. Giorgetti, CNIT, Pisa, Italy / F. Cugini, CNIT, Pisa, Italy / A. Sgambelluri, CNIT, Pisa, Italy / R. Nejabati, University of Bristol, Bristol, UK / D. Simeonidou, University of Bristol, Bristol, UK / R.-P. Braun, Deutsche Telekom, Germany / A. Autenrieth, ADVA, Munich, Germany / J.-P. Elbers, ADVA, Munich, Germany / J. K. Fischer, Fraunhofer HHI, Berlin, Germany / R. Freund, Fraunhofer HHI, Berlin, Germany
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Knowledge management in optical networks: architecture, methods, and use cases [Invited]

  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Tabatabaeimehr, Fatemehsadat|||0000-0003-4498-4219
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
© [2019 Optical Society of America]. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved., Autonomous network operation realized by means of control loops, where prediction from machine learning (ML) models is used as input to proactively reconfigure individual optical devices or the whole optical network, has been recently proposed to minimize human intervention. A general issue in this approach is the limited accuracy of ML models due to the lack of real data for training the models. Although the training dataset can be complemented with data from lab experiments and simulation, it is probable that once in operation, events not considered during the training phase appear and thus lead to model inaccuracies. A feasible solution is to implement self-learning approaches, where model inaccuracies are used to re-train the models in the field and to spread such data for training models being used for devices of the same type in other nodes in the network. In this paper, we develop the concept of collective self-learning aiming at improving the model’s error convergence time as well as at minimizing the amount of data being shared and stored. To this end, we propose a knowledge management (KM) process and an architecture to support it. Besides knowledge usage, the KM process entails knowledge discovery, knowledge sharing, and knowledge assimilation. Specifically, knowledge sharing and assimilation are based on distributing and combining ML models, so specific methods are proposed for combining models. Two use cases are used to evaluate the proposed KM architecture and methods. Exhaustive simulation results show that model-based KM provides the best error convergence time with reduced data being shared., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Building autonomic optical whitebox-based networks

  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Sgambelluri, Andrea
  • Casellas Regi, Ramón
  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis|||0000-0003-4013-9712
  • Fresi, Francesco
  • Paolucci, Francesco
  • Martínez Rivera, Ricardo Victor
  • Riccardi, Emilio
Disaggregation at the optical layer is expected to bring benefits to network operators by enriching the offering of available solutions and enabling the deployment of optical nodes that better fit their needs. In this paper, we assume a partially disaggregated model with transponder nodes for transmission and ROADMs for switching, where each optical node is conceived as a whitebox consisting of a set of optical devices and a local node controller that exposes a single interface to the software-defined networks (SDN) controller. An architecture to provide autonomic networking is proposed, including the SDN controller and supporting monitoring and data analytics capabilities; YANG data models and software interfaces have been specifically tailored to deal with the level of disaggregation desired. To demonstrate the concept of autonomic networking, use cases for provisioning and self-tuning based on the monitoring of optical spectrum have been proposed and experimentally assessed in a distributed test-bed connecting laboratories in Spain and Italy., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Dedicated protection with signal overlap in elastic optical networks

  • Cugini, Filippo
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Foggi, Tommaso
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Sambo, Nicola
  • Castoldi, Piero
In optical dedicated path protection (1 1), the same optical signal is transmitted along both working and backup paths. Thus, in 1 1, the transmission parameters need to be configured according to the most impaired path, e.g., the backup one. This implies that the working signal is typically served with higher than necessary quality of transmission and occupies larger than necessary spectrum resources, leading to inefficient network resource utilization. In this study, we propose to apply the recently introduced signal overlap technique to improve network efficiency of optical dedicated path protection. The signal overlap technique enables uncorrelated optical signals to be superimposed along the same spectrum resources. It relies on a cancellation detection strategy also exploited in wireless communications and recently applied on coherent optical receivers. In particular, this study summarizes the key aspect and transmission performance of the overlap technique and discusses its implementation complexity. Then, two signal overlap schemes, namely, working signal overlap and working and backup signal overlap are introduced for effective optical dedicated path protection. An integer linear programming (ILP) formulation based on the routing, modulation, and spectrum allocation problem and an efficient heuristic are then presented to effectively assess the performance of the proposed overlap-based 1 1 protection strategy under various topologies and traffic profiles. In the considered simulative scenarios (e.g., network diameters well below a thousand kilometers), results show that the more efficient working and backup signal overlap scheme significantly improves the accepted load of dedicated protection requests., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Learning from the optical spectrum: failure detection and identification [Invited]

  • Shariati, Mohammad Behnam
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Comellas Colomé, Jaume|||0000-0002-9129-0562
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, The availability of coarse-resolution cost-effective Optical Spectrum Analyzers (OSA) allows its widespread deployment in operators’ networks. In this paper, we explore several machine learning approaches for soft-failure detection, identification and localization that take advantage of OSAs. In particular, we present three different solutions for the two most common filter-related soft-failures; filter shift and tight filtering which noticeably deform the expected shape of the optical spectrum. However, filter cascading is a key challenge as it affects the shape of the optical spectrum similarly to tight filtering; the approaches are specifically designed to avoid the misclassification of properly operating signals when normal filter cascading effects are present. The proposed solutions are: $i) multi-classifier$ approach, which uses features extracted directly from the optical spectrum, $ii) single-classifier$ approach, which uses pre-processed features to compensate for filter cascading, and $iii) residual-based$ approach, which uses a residual signal computed from subtracting the acquired single by OSAs from an expected signal synthetically generated. Extensive numerical results are ultimately presented to compare the performance of the proposed approaches in terms of accuracy and robustness., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

SDN-controlled and orchestrated OPSquare DCN enabling automatic network slicing with differentiated QoS provisioning

  • Xue, Xuwei
  • Wang, Fu
  • Agraz Bujan, Fernando|||0000-0001-8958-0088
  • Pagès Cruz, Albert|||0000-0002-6661-3630
  • Pan, Bitao
  • Yan, Fulong
  • Guo, Xiaojun
  • Spadaro, Salvatore|||0000-0002-4100-1726
  • Calabretta, Nicola
© 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, Optical switching techniques have the potential to enable the optical data center network (DCN) interconnections providing high capacity and fast switching capabilities, overcoming thus the bandwidth and latency bottleneck of present electrical switch-based multi-tiered DCNs. The rapid growth of multi-tenant applications with heterogeneous traffic require specialized quality of service (QoS) in terms of packet loss and latency to the DCN infrastructure. Slicing the DCNs into dedicated pieces according to the deployed applications, differentiated QoS, and high resource utilization can be provided. However, slicing the optical DCNs still needs to be investigated because the Software-defined Networking (SDN) technique is developed for the electrical networks, not fully supporting the properties of the optical network. Additionally, Network Slices (NS) need to be automatically provisioned and reconfigured, to provide flexible slice interconnections in support of the multi-tenant applications to be deployed. In this article, we propose and experimentally assess the automatic and flexible NSs configurations of optical OPSquare DCN controlled and orchestrated by an extended SDN control plane for multi-tenant applications with differentiated QoS provisioning. Optical Flow Control (OFC) protocol has been developed to prevent packet losses at switch sides caused by packet contentions. The extended OpenFlow (OF) protocol of SDN is deployed as well in support of the optical switching characteristics. Based on the collected resource topology of data plane, the optical network slices can be dynamically provisioned and automatically reconfigured by the SDN control plane. Meanwhile, experimental results validate that the priority assignment of application flows supplies dynamic QoS performance to various slices running applications with specific requirements in terms of packet loss and transmission latency. In addition, the capability of exposing traffic statistics information of data plane to SDN control plane enables the implementation of load balancing algorithms further improving the network performance with high QoS. No packet loss and less than 4.8 µs server-to-server latency can be guaranteed for the sliced network with highest priority at a load of 0.5., This work is supported by Olympics project (ESTAR17207) and Metro-Haul project (G.A. 761727)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

An architecture to support autonomic slice networking

  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis|||0000-0003-4013-9712
  • Paolucci, Francesco
  • Vela, Alba P.
  • Sgambelluri, Andrea
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Cugini, Filippo
IEEE Network slices combine resource virtualization with the isolation level required by future 5G applications. In addition, the use of monitoring and data analytics help to maintain the required network performance, while reducing total cost of ownership. In this paper, an architecture to enable autonomic slice networking is presented. Extended nodes make local decisions close to network devices, whereas centralized domain systems collate and export metered data transparently to customer controllers, all of them leveraging customizable and isolated data analytics processes. Discovered knowledge can be applied for both proactive and reactive network slice reconfiguration, triggered either by service providers or customers, thanks to the interaction with state-of-the-art software-defined networking controllers and planning tools. The architecture is experimentally demonstrated by means of a complex use case for a multi-domain multilayer MPLS-over-optical network. In particular, the use case consists of the following Observe-Analyze-Act loops: i) proactive network slice rerouting after BER degradation detection in a lightpath supporting a virtual link (vlink); ii) reactive core network restoration after optical link failure; and iii) reactive network slice rerouting after the degraded lightpath is restored. The proposed architecture is experimentally validated on a distributed testbed connecting premises in UPC (Spain) and CNIT (Italy)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Supporting time-sensitive and best-effort traffic on a common metro infrastructure

  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
© 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., Considerable research and standardization efforts are being made to support time-sensitive traffic, e.g., generated by applications like Industry 4.0 and 5G fronthaul, on packet networks. This letter focuses on analyzing the impact of conveying time-sensitive traffic in operators’ networks when such traffic is mixed with best-effort traffic. Extensions to a continuous $G/G/1/k$ queue model are proposed to evaluate two different Ethernet technologies, synchronous and asynchronous, supporting time-sensitive flows in terms of their influence on the performance of best-effort traffic. Results highlight pros and cons of those technologies to protect best-effort performance., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016- 2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Proactive defragmentation in elastic optical networks under dynamic load conditions

  • Comellas Colomé, Jaume|||0000-0002-9129-0562
  • Vicario, L.
  • Junyent Giralt, Gabriel|||0000-0003-0059-7700
The final publication is available at Springer via http://dx.doi.org/10.1007/s11107-018-0767-7, The main weakness of elastic optical networks (EON), under dynamic traffic conditions, stems from spectrum fragmentation. A lot of research efforts have been dedicated during recent years to spectrum defragmentation. In this work, a thorough study about proactive defragmentation is carried out. Effects of the different defragmentation parameters on the EON performance are analyzed, and appropriate values of the defragmentation period, which guarantee suitable network performance while keeping the network control complexity at reasonable values, are obtained by means of extensive simulations. Benefit obtained by applying different defragmentation strategies, in terms of increase in the supported load at a given bandwidth blocking probability, is also reported. Different traffic conditions and network topologies are simulated to assess the validity of the obtained results., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Autonomic disaggregated multilayer networking

  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis|||0000-0003-4013-9712
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
Focused on reducing capital expenditures by opening the data plane to multiple vendors without impacting performance, node disaggregation is attracting the interest of network operators. Although the software-defined networking (SDN) paradigm is key for the control of such networks, the increased complexity of multilayer networks strictly requires monitoring/telemetry and data analytics capabilities to assist in creating and operating self-managed (autonomic) networks. Such autonomicity greatly reduces operational expenditures, while improving network performance. In this context, a monitoring and data analytics (MDA) architecture consisting of centralized data storage with data analytics capabilities, together with a generic node agent for monitoring/telemetry supporting disaggregation, is presented. A YANG data model that allows one to clearly separate responsibilities for monitoring configuration from node configuration is also proposed. The MDA architecture and YANG data models are experimentally demonstrated through three different use cases: i) virtual link creation supported by an optical connection, where monitoring is automatically activated; ii) multilayer self-configuration after bit error rate (BER) degradation detection, where a modulation format adaptation is recommended for the SDN controller to minimize errors (this entails reducing the capacity of both the virtual link and supported multiprotocol label switching-transport profile (MPLS-TP) paths); and iii) optical layer selfhealing, including failure localization at the optical layer to find the cause of BER degradation. A combination of active and passive monitoring procedures allows one to localize the cause of the failure, leading to lightpath rerouting recommendations toward the SDN controller avoiding the failing element(s)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Brokered orchestration for end-to-end service provisioning across heterogeneous multi-operator (Multi-AS) optical networks

  • Castro Casales, Alberto
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Gifre Renom, Lluís
  • Chen, Cen
  • Yin, Jie
  • Zhu, Zuqing
  • Proietti, Roberto
  • Yoo, Sung-Joo Ben
This paper proposes a new networking paradigm introducing the broker-plane above the management planes of Autonomous Systems (ASes). The brokers communicate with the manager of each AS to assist coordinate end-to-end resource management and path provisioning across the multi-AS networks involving multiple operators. The broker plane updates the virtual network topology, manages the resource information of inter-AS links and aggregated (abstracted) intra-AS links, and computes end-to-end routing, modulation formats, and spectrum assignment (RMSA). Notwithstanding, due to the different dynamicity of each AS, the probability of finding a multi-AS transparent path fulfilling the spectrum continuity and contiguity constraints might be low. To improve the grade of the inter-domain connectivity service, spectrum converters can be installed in inter-domain nodes or per-AS defragmentation can be performed with a global view. In this paper, we introduce a mechanism where each AS can advertise its internal capabilities, e.g., spectrum conversion, their ability to implement spectrum defragmentation or any other network feature. The Multi-AS RMSA with Defragmentation Capability problem is presented and mathematically modeled. A heuristic algorithm is designed to solve it. The mechanism's workflow is comprehensively tested using simulations. Results show connection blocking reduction as high as 26%, clearly validating the benefits of the proposed mechanism. Finally, its experimental assessment was conducted on a distributed multi-continental testbed., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

CURSA-SQ: a methodology for service-centric traffic flow analysis

  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Coltraro, Franco|||0000-0002-9149-950X
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The rapid availability of new services means that network operators cannot exhaustively test their impact on the network or anticipate any capacity exhaustion. This situation will be worse with the imminent introduction of 5G technology and the kind of totally new services that it will support. In addition, the increasing complexity of the network makes analyzing its behavior challenging against the specific traffic that needs to be supported; this prevents from training human operators and, much less, machine learning algorithms that might automatize network operation. In this paper, we present CURSA-SQ, a methodology to analyze network behavior when specific traffic that would be generated by groups of service consumers is injected. CURSA-SQ includes input traffic flow modeling with second and sub-second granularity based on specific service and consumer behavior, as well as a continuous G/G/1/k queue model based on the logistic function. The methodology allows for accurately studying the traffic flows at the input and outputs of complex scenarios with multiples queue systems, as well as other metrics such as delays, while showing noticeable scalability. Application use cases include packet and optical network planning, service introduction assessment, and autonomic networking, just to mention a few., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

A control and management architecture supporting autonomic NFV services

  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Casellas Regi, Ramón
  • Llana, Sergio
  • Gifre Renom, Lluís
  • Martínez Rivera, Ricardo Victor
  • Vilata, Ricard
  • Muñoz González, Raül
  • Ruiz, Marc
The proposed control, orchestration and management (COM) architecture is presented from a high-level point of view; it enables the dynamic provisioning of services such as network data connectivity or generic network slicing instances based on virtual network functions (VNF). The COM is based on Software Defined Networking (SDN) principles and is hierarchical, with a dedicated controller per technology domain. Along with the SDN control plane for the provisioning of connectivity, an ETSI NFV management and orchestration system is responsible for the instantiation of Network Services, understood in this context as interconnected VNFs. A key, novel component of the COM architecture is the monitoring and data analytics (MDA) system, able to collect monitoring data from the network, datacenters and applications which outputs can be used to proactively reconfigure resources thus adapting to future conditions, like load or degradations. To illustrate the COM architecture, a use case of a Content Delivery Network service taking advantage of the MDA ability to collect and deliver monitoring data is experimentally demonstrated., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

The dichotomy of distributed and centralized control: METRO-HAUL, when control planes collide for 5G networks

  • King, Daniel
  • Farrel, Adrian
  • King, Emiko Nishida
  • Casellas Regi, Ramon
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Nejabati, Reza
  • Lord, Andrew
Automating the provisioning of 5G services, deployed over a heterogeneous infrastructure (in terms of domains, technologies, and management platforms), remains a complex task, yet driven by the constant need to provide end-to-end connections at network slices at reducing costs and service deployment time. At the same time, such services are increasingly conceived around interconnected functions and require allocation of computing, storage, and networking resources. The METRO-HAUL 5G research initiative acknowledges the need for automation and strives to develop an orchestration platform for services and resources that extends, integrates, and builds on top of existing approaches, macroscopically adopting Transport Software Defined Networking principles, and leveraging the programmability and open control of Transport SDN., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Dynamic core VNT adaptability based on predictive metro-flow traffic models

  • Morales Alcaide, Fernando|||0000-0001-7337-1775
  • Gifre Renom, Lluís
  • Paolucci, Francesco
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Cugini, Filippo
  • Castoldi, Piero
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
© 2017 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., MPLS-over-optical virtual network topologies (VNTs) can be adapted to near-future traffic matrices based on predictive models that are estimated by applying data analytics on monitored origin-destination (OD) traffic. However, the deployment of independent SDN controllers for core and metro segments can bring large inefficiencies to this core network reconfiguration based on traffic prediction when traffic flows from metro areas are rerouted to different ingress nodes in the core. In such cases, OD traffic patterns in the core might severely change, thus affecting the quality of the predictive OD models. New traffic model re-estimation usually takes a long time, during which no predictive capabilities are available for the network operator. To alleviate this problem, we propose to extend data analytics to metro networks to obtain predictive models for the metro flows; by knowing how these flows are aggregated into OD pairs in the core, we can also aggregate their predictive models, thus accurately predicting OD traffic and therefore enabling core VNT reconfiguration. To obtain quality metro-flow models, we propose an estimation algorithmthat processes monitored data and returns a predictive model. In addition, a flow controller is proposed for the control architecture to allow metro and core controllers to exchange metro-flow model information. The proposed model aggregation is evaluated through exhaustive simulation, and eventually experimentally assessed together with the flow controller in a testbed connecting premises in CNIT (Pisa, Italy) and UPC (Barcelona, Spain)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Learning life cycle to speed up autonomic optical transmission and networking adoption

  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
  • Shariati, Mohammad Behnam
  • Boitier, Fabien
  • Layec, Patricia
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
Autonomic optical transmission and networking requires machine learning (ML) models to be trained with large datasets. However, the availability of enough real data to produce accurate ML models is rarely ensured since new optical equipment and techniques are continuously being deployed in the network. One option is to generate data from simulations and lab experiments, but such data could not cover the whole features space and would translate into inaccuracies in the ML models. In this paper, we propose an ML-based algorithm life cycle to facilitate ML deployment in real operator networks. The dataset for ML training can be initially populated based on the results from simulations and lab experiments. Once ML models are generated, ML retraining can be performed after inaccuracies are detected to improve their precision. Illustrative numerical results show the benefits of the proposed learning cycle for general use cases. In addition, two specific use cases are proposed and demonstrated that implement different learning strategies: (i) a two-phase strategy performing out-of-field training using data from simulations and lab experiments with generic equipment, followed by an in-field adaptation to support heterogeneous equipment (the accuracy of this strategy is shown for a use case of failure detection and identification), and (ii) in-field retraining, where ML models are retrained after detecting model inaccuracies. Different approaches are analyzed and evaluated for a use case of autonomic transmission, where results show the significant benefits of collective learning., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Modeling and assessing connectivity services performance in a sandbox domain

  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Ruiz Noguera, Mario
  • Tabatabaeimehr, Fatemehsadat|||0000-0003-4498-4219
  • Gifré Renom, Lluís
  • López-Buedo, Sergio
  • López de Vergara Méndez, Jorge E.
  • González de Dios, Oscar
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
©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., The automation of Network Services (NS) consisting of virtual functions connected through a multilayer packet-over-optical network requires predictable Quality of Service (QoS) performance, measured in terms of throughput and latency, to allow making proactive decisions. QoS is typically guaranteed by overprovisioning capacity dedicated to the NS, which increases costs for customers and network operators, especially when the traffic generated by the users and/or the virtual functions highly varies over the time. This article presents the PILOT methodology for modeling the performance of connectivity services during commissioning testing in terms of throughput and latency. Benefits are double: first, an accurate per-connection model allows operators to better operate their networks and reduce the need for overprovisioning; and second, customers can tune their applications to the performance characteristics of the connectivity. PILOT runs in a sandbox domain and constructs a scenario where an efficient traffic flow simulation environment, based on the CURSA-SQ model, is used to generate large amounts of data for Machine Learning (ML) model training and validation. The simulation scenario is tuned using real measurements of the connection (including throughput and latency) obtained from a set of active probes in the operator network. PILOT has been experimentally validated on a distributed testbed connecting UPC and Telefónica premises., This work was partially supported by the EC through the METRO-HAUL (G.A. nº 761727) project, from the Spanish MINECO/FEDER TWINS (TEC2017-90097-R) and TRÁFICA (TEC2015-69417-C2-1-R) projects and from the Catalan Institution for Research and Advanced Studies., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Near real-time estimation of end-to-end performance in converged fixed-mobile networks

  • Bernal Escribano, Álvaro
  • Richart Gutiérrez, Matías Mario|||0000-0002-9152-3522
  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Castro Casales, Alberto
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
© <2019> Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The independent operation of mobile and fixed network segments is one of the main barriers that prevents improving network performance while reducing capital expenditures coming from overprovisioning. In particular, a coordinated dynamic network operation of both network segments is essential to guarantee end-to-end Key Performance Indicators (KPI), on which new network services rely on. To achieve such dynamic operation, accurate estimation of end-to-end KPIs is needed to trigger network reconfiguration before performance degrades. In this paper, we present a methodology to achieve an accurate, scalable, and predictive estimation of end-to-end KPIs with sub-second granularity near real-time in converged fixed-mobile networks. Specifically, we extend our CURSA-SQ methodology for mobile network traffic analysis, to enable converged fixed-mobile network operation. CURSA-SQ combines simulation and machine learning fueled with real network monitoring data. Numerical results validate the accuracy, robustness, and usability of the proposed CURSA-SQ methodology for converged fixed-mobile network scenarios., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Predictive autonomic transmission for low-cost low-margin metro optical networks

  • Ruiz Ramírez, Marc|||0000-0001-6429-6347
  • Boitier, Fabien
  • Shariati, Mohammad Behnam
  • Layec, Patricia
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
Low-cost low-margin implementation plays an essential role in upgrading optical metro networks required for future 5G ecosystem. In this regard, low-resolution analog-to-digital converters can be used in coherent optical transponders to reduce cost and power consumption. However, the resulting transmission systems become more sensitive to physical layer fluctuations like the events caused by fiber stressing. Such fluctuations might have a strong impact on the quality of transmission (QoT) of the signals. To guarantee robust operation, soft decision forward error correction (FEC) techniques are required to guarantee zero post-FEC bit error rate (BER) transmission, which could increase the power consumption of the receiver and thus operational expenses. In this paper, we aim at minimizing power consumption while keeping zero post-FEC errors by means of a predictive autonomic transmission agent (ATA) based on machine learning. We present a sophisticated ATA model that, taking advantage of real-time monitoring of state of polarization traces and the corresponding pre-FEC BER, predicts the right FEC configuration for short-term operation, thus requiring minimum power consumption. In addition, we propose a complementary long-term prediction of excessive pre-FEC BER to enable remote reconfiguration at the transmitter side through the network controller. A set of experimental measurements is used to train and validate the proposed ATA system. Exhaustive numerical analysis allows concluding that ATA based on artificial neural network predictors achieves the maximum QoT robustness with 80% power consumption reductions compared to static FEC configuration., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016-2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Machine learning for network automation: Overview, architecture, and applications [invited tutorial]

  • Rafique, Danish
  • Velasco Esteban, Luis Domingo|||0000-0002-7345-296X
Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis., Peer Reviewed
Repositorio Digital UPCT
Publication Artículo científico (JournalArticle)

A genetic algorithm for VNF provisioning in NFV-enabled cloud/MEC RAN architectures

  • Ruiz Pérez, Lidia
  • Durán Barroso, Ramón José
  • Miguel Jiménez, Ignacio de
  • Khodashenas, Pouria Sayyad
  • Pedreño Manresa, José Juan
  • Merayo Álvarez, Noemí
  • Aguado Manzano, Juan Carlos
  • Pavón Mariño, Pablo
  • Siddiqui, Shuaib
  • Mata, Javier
  • Fernández Reguero, Patricia
  • Lorenzo Toledo, Rubén Mateo
  • Abril Domingo, Evaristo José
5G technologies promise to bring new network and service capacities and are expected to introduce significant architectural and service deployment transformations. The Cloud-Radio Access Networks (C-RAN) architecture, enabled by the combination of Software Defined Networking (SDN), Network Function Virtualization (NFV) and Mobile Edge Computing (MEC) technologies, play a key role in the development of 5G. In this context, this paper addresses the problems of Virtual Network Functions (VNF) provisioning (VNF-placement and service chain allocation) in a 5G network. In order to solve that problem, we propose a genetic algorithm that, considering both computing resources and optical network capacity, minimizes both the service blocking rate and CPU usage. In addition, we present an algorithm extension that adds a learning stage and evaluate the algorithm performance benefits in those scenarios where VNF allocations can be reconfigured. Results reveal and quantify the advantages of reconfiguring the VNF mapping depending on the current demands. Our methods outperform previous proposals in the literature, reducing the service blocking ratio while saving energy by reducing the number of active core CPUs, Ministerio de Economía, Industria y Competitividad (Project TEC2014-53071-C3-2-P, TEC2017-84423-C3-1-P, TEC2015-71932-REDT) Ministerio de Educación, Cultura y Deporte (Proyect BES-2015-074514 and FPU14/04227
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Brokered orchestration for end-to-end service provisioning across heterogeneous multi-operator (Multi-AS) optical networks

  • Castro Casales, Alberto
  • Velasco Esteban, Luis Domingo
  • Gifre Renom, Lluís
  • Chen, Cen
  • Yin, Jie
  • Zhu, Zuqing
  • Proietti, Roberto
  • Yoo, Sung-Joo Ben
This paper proposes a new networking paradigm introducing the broker-plane above the management planes of Autonomous Systems (ASes). The brokers communicate with the manager of each AS to assist coordinate end-to-end resource management and path provisioning across the multi-AS networks involving multiple operators. The broker plane updates the virtual network topology, manages the resource information of inter-AS links and aggregated (abstracted) intra-AS links, and computes end-to-end routing, modulation formats, and spectrum assignment (RMSA). Notwithstanding, due to the different dynamicity of each AS, the probability of finding a multi-AS transparent path fulfilling the spectrum continuity and contiguity constraints might be low. To improve the grade of the inter-domain connectivity service, spectrum converters can be installed in inter-domain nodes or per-AS defragmentation can be performed with a global view. In this paper, we introduce a mechanism where each AS can advertise its internal capabilities, e.g., spectrum conversion, their ability to implement spectrum defragmentation or any other network feature. The Multi-AS RMSA with Defragmentation Capability problem is presented and mathematically modeled. A heuristic algorithm is designed to solve it. The mechanism's workflow is comprehensively tested using simulations. Results show connection blocking reduction as high as 26%, clearly validating the benefits of the proposed mechanism. Finally, its experimental assessment was conducted on a distributed multi-continental testbed., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Real-time optical spectrum monitoring in filterless optical metro networks

  • Shariati, Mohammad Behnam
  • Ruiz Ramírez, Marc
  • Fresi, Francesco
  • Sgambelluri, Andrea
  • Cugini, Filippo
  • Velasco Esteban, Luis Domingo
The final publication is available at Springer via http://dx.doi.org/10.1007/s11107-020-00890-z, Filterless optical networks (FONs) have been proposed as a feasible solution for optical metro networks. In addition, as a result of the shorter distance compared to core optical networks, direct detection optical transmission systems can be used in metro FONs, which reduces costs, as compared to coherent detection systems. In this work, we present two optical signal tracking approaches for FONs that allow to detect small frequency laser drift problems and enable safely reducing channel spacing. Additionally, we study the most proper resolution for optical spectrum analyzers continuously scanning the whole C-band. Proposed approaches are: (1) feature-based tracking and (2) residual-based tracking. Experiments are carried out to compare the performance of the approaches for both direct detection and coherent detection systems, in the case of a single optical signal with no neighboring signals nearby in the spectrum, as well as in the case of a group of optical signals closely allocated in the spectrum. The results show that the residual-based approach enriched with contextual information enables to better track and correct the wavelength drifts before they reach their limits (e.g.,¿±¿2.5 GHz), leading to the guard band reduction for what concerns wavelength drifts., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016-2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Dynamic core VNT adaptability based on predictive metro-flow traffic models

  • Morales Alcaide, Fernando
  • Gifre Renom, Lluís
  • Paolucci, Francesco
  • Ruiz Ramírez, Marc
  • Cugini, Filippo
  • Castoldi, Piero
  • Velasco Esteban, Luis Domingo
© 2017 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., MPLS-over-optical virtual network topologies (VNTs) can be adapted to near-future traffic matrices based on predictive models that are estimated by applying data analytics on monitored origin-destination (OD) traffic. However, the deployment of independent SDN controllers for core and metro segments can bring large inefficiencies to this core network reconfiguration based on traffic prediction when traffic flows from metro areas are rerouted to different ingress nodes in the core. In such cases, OD traffic patterns in the core might severely change, thus affecting the quality of the predictive OD models. New traffic model re-estimation usually takes a long time, during which no predictive capabilities are available for the network operator. To alleviate this problem, we propose to extend data analytics to metro networks to obtain predictive models for the metro flows; by knowing how these flows are aggregated into OD pairs in the core, we can also aggregate their predictive models, thus accurately predicting OD traffic and therefore enabling core VNT reconfiguration. To obtain quality metro-flow models, we propose an estimation algorithmthat processes monitored data and returns a predictive model. In addition, a flow controller is proposed for the control architecture to allow metro and core controllers to exchange metro-flow model information. The proposed model aggregation is evaluated through exhaustive simulation, and eventually experimentally assessed together with the flow controller in a testbed connecting premises in CNIT (Pisa, Italy) and UPC (Barcelona, Spain)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

CURSA-SQ: a methodology for service-centric traffic flow analysis

  • Ruiz Ramírez, Marc
  • Coltraro, Franco
  • Velasco Esteban, Luis Domingo
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The rapid availability of new services means that network operators cannot exhaustively test their impact on the network or anticipate any capacity exhaustion. This situation will be worse with the imminent introduction of 5G technology and the kind of totally new services that it will support. In addition, the increasing complexity of the network makes analyzing its behavior challenging against the specific traffic that needs to be supported; this prevents from training human operators and, much less, machine learning algorithms that might automatize network operation. In this paper, we present CURSA-SQ, a methodology to analyze network behavior when specific traffic that would be generated by groups of service consumers is injected. CURSA-SQ includes input traffic flow modeling with second and sub-second granularity based on specific service and consumer behavior, as well as a continuous G/G/1/k queue model based on the logistic function. The methodology allows for accurately studying the traffic flows at the input and outputs of complex scenarios with multiples queue systems, as well as other metrics such as delays, while showing noticeable scalability. Application use cases include packet and optical network planning, service introduction assessment, and autonomic networking, just to mention a few., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Predictive autonomic transmission for low-cost low-margin metro optical networks

  • Ruiz Ramírez, Marc
  • Boitier, Fabien
  • Shariati, Mohammad Behnam
  • Layec, Patricia
  • Velasco Esteban, Luis Domingo
Low-cost low-margin implementation plays an essential role in upgrading optical metro networks required for future 5G ecosystem. In this regard, low-resolution analog-to-digital converters can be used in coherent optical transponders to reduce cost and power consumption. However, the resulting transmission systems become more sensitive to physical layer fluctuations like the events caused by fiber stressing. Such fluctuations might have a strong impact on the quality of transmission (QoT) of the signals. To guarantee robust operation, soft decision forward error correction (FEC) techniques are required to guarantee zero post-FEC bit error rate (BER) transmission, which could increase the power consumption of the receiver and thus operational expenses. In this paper, we aim at minimizing power consumption while keeping zero post-FEC errors by means of a predictive autonomic transmission agent (ATA) based on machine learning. We present a sophisticated ATA model that, taking advantage of real-time monitoring of state of polarization traces and the corresponding pre-FEC BER, predicts the right FEC configuration for short-term operation, thus requiring minimum power consumption. In addition, we propose a complementary long-term prediction of excessive pre-FEC BER to enable remote reconfiguration at the transmitter side through the network controller. A set of experimental measurements is used to train and validate the proposed ATA system. Exhaustive numerical analysis allows concluding that ATA based on artificial neural network predictors achieves the maximum QoT robustness with 80% power consumption reductions compared to static FEC configuration., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016-2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Building autonomic optical whitebox-based networks

  • Velasco Esteban, Luis Domingo
  • Sgambelluri, Andrea
  • Casellas Regi, Ramón
  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis
  • Fresi, Francesco
  • Paolucci, Francesco
  • Martínez Rivera, Ricardo Victor
  • Riccardi, Emilio
Disaggregation at the optical layer is expected to bring benefits to network operators by enriching the offering of available solutions and enabling the deployment of optical nodes that better fit their needs. In this paper, we assume a partially disaggregated model with transponder nodes for transmission and ROADMs for switching, where each optical node is conceived as a whitebox consisting of a set of optical devices and a local node controller that exposes a single interface to the software-defined networks (SDN) controller. An architecture to provide autonomic networking is proposed, including the SDN controller and supporting monitoring and data analytics capabilities; YANG data models and software interfaces have been specifically tailored to deal with the level of disaggregation desired. To demonstrate the concept of autonomic networking, use cases for provisioning and self-tuning based on the monitoring of optical spectrum have been proposed and experimentally assessed in a distributed test-bed connecting laboratories in Spain and Italy., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

An architecture to support autonomic slice networking

  • Velasco Esteban, Luis Domingo
  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis
  • Paolucci, Francesco
  • Vela, Alba P.
  • Sgambelluri, Andrea
  • Ruiz Ramírez, Marc
  • Cugini, Filippo
IEEE Network slices combine resource virtualization with the isolation level required by future 5G applications. In addition, the use of monitoring and data analytics help to maintain the required network performance, while reducing total cost of ownership. In this paper, an architecture to enable autonomic slice networking is presented. Extended nodes make local decisions close to network devices, whereas centralized domain systems collate and export metered data transparently to customer controllers, all of them leveraging customizable and isolated data analytics processes. Discovered knowledge can be applied for both proactive and reactive network slice reconfiguration, triggered either by service providers or customers, thanks to the interaction with state-of-the-art software-defined networking controllers and planning tools. The architecture is experimentally demonstrated by means of a complex use case for a multi-domain multilayer MPLS-over-optical network. In particular, the use case consists of the following Observe-Analyze-Act loops: i) proactive network slice rerouting after BER degradation detection in a lightpath supporting a virtual link (vlink); ii) reactive core network restoration after optical link failure; and iii) reactive network slice rerouting after the degraded lightpath is restored. The proposed architecture is experimentally validated on a distributed testbed connecting premises in UPC (Spain) and CNIT (Italy)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

A control and management architecture supporting autonomic NFV services

  • Velasco Esteban, Luis Domingo
  • Casellas Regi, Ramón
  • Llana, Sergio
  • Gifre Renom, Lluís
  • Martínez Rivera, Ricardo Victor
  • Vilata, Ricard
  • Muñoz González, Raül
  • Ruiz, Marc
The proposed control, orchestration and management (COM) architecture is presented from a high-level point of view; it enables the dynamic provisioning of services such as network data connectivity or generic network slicing instances based on virtual network functions (VNF). The COM is based on Software Defined Networking (SDN) principles and is hierarchical, with a dedicated controller per technology domain. Along with the SDN control plane for the provisioning of connectivity, an ETSI NFV management and orchestration system is responsible for the instantiation of Network Services, understood in this context as interconnected VNFs. A key, novel component of the COM architecture is the monitoring and data analytics (MDA) system, able to collect monitoring data from the network, datacenters and applications which outputs can be used to proactively reconfigure resources thus adapting to future conditions, like load or degradations. To illustrate the COM architecture, a use case of a Content Delivery Network service taking advantage of the MDA ability to collect and deliver monitoring data is experimentally demonstrated., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Proactive defragmentation in elastic optical networks under dynamic load conditions

  • Comellas Colomé, Jaume
  • Vicario, L.
  • Junyent Giralt, Gabriel
The final publication is available at Springer via http://dx.doi.org/10.1007/s11107-018-0767-7, The main weakness of elastic optical networks (EON), under dynamic traffic conditions, stems from spectrum fragmentation. A lot of research efforts have been dedicated during recent years to spectrum defragmentation. In this work, a thorough study about proactive defragmentation is carried out. Effects of the different defragmentation parameters on the EON performance are analyzed, and appropriate values of the defragmentation period, which guarantee suitable network performance while keeping the network control complexity at reasonable values, are obtained by means of extensive simulations. Benefit obtained by applying different defragmentation strategies, in terms of increase in the supported load at a given bandwidth blocking probability, is also reported. Different traffic conditions and network topologies are simulated to assess the validity of the obtained results., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Learning from the optical spectrum: failure detection and identification [Invited]

  • Shariati, Mohammad Behnam
  • Ruiz Ramírez, Marc
  • Comellas Colomé, Jaume
  • Velasco Esteban, Luis Domingo
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, The availability of coarse-resolution cost-effective Optical Spectrum Analyzers (OSA) allows its widespread deployment in operators’ networks. In this paper, we explore several machine learning approaches for soft-failure detection, identification and localization that take advantage of OSAs. In particular, we present three different solutions for the two most common filter-related soft-failures; filter shift and tight filtering which noticeably deform the expected shape of the optical spectrum. However, filter cascading is a key challenge as it affects the shape of the optical spectrum similarly to tight filtering; the approaches are specifically designed to avoid the misclassification of properly operating signals when normal filter cascading effects are present. The proposed solutions are: $i) multi-classifier$ approach, which uses features extracted directly from the optical spectrum, $ii) single-classifier$ approach, which uses pre-processed features to compensate for filter cascading, and $iii) residual-based$ approach, which uses a residual signal computed from subtracting the acquired single by OSAs from an expected signal synthetically generated. Extensive numerical results are ultimately presented to compare the performance of the proposed approaches in terms of accuracy and robustness., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Machine learning for network automation: Overview, architecture, and applications [invited tutorial]

  • Rafique, Danish
  • Velasco Esteban, Luis Domingo
Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Demonstration of latency-aware 5G network slicing on optical metro networks

  • Shariati, Mohammad Behnam
  • Velasco Esteban, Luis Domingo
  • Pedreno Manresa, José Juan
  • Dochhan, Annika
  • Casellas Regi, Ramon
  • Siddique Muqaddas, Abubakar
  • González de Dios, Oscar
  • Luque Canto, L.
  • Lent, Bodo
  • Ruiz Ramírez, Marc
The H2020 METRO-HAUL European project has architected a latency-aware, cost-effective, agile, and programmable optical metro network. This includes the design of semi-disaggregated metro nodes with compute and storage capabilities, which interface effectively with both 5G access and multi-Tbit/s elastic optical networks in the core. In this paper, we report the automated deployment of 5G services, in particular, a public safety video surveillance use case employing low-latency object detection and tracking using on-camera and on-the-edge analytics. The demonstration features flexible deployment of network slice instances, implemented in terms of ETSI NFV Network Services. We summarize the key findings in a detailed analysis of end-to-end quality of service, service setup time, and soft-failure detection time. The results show that the round-trip-time over an 80 km link is under 800 µs and the service deployment time under 180 seconds., Horizon 2020 Framework Programme (761727); Bundesministerium für Bildung und Forschung (16KIS0979K)., Peer Reviewed, Article signat per 25 autors/es: B. Shariati, Fraunhofer HHI, Berlin, Germany / L. Velasco, Universitat Politècnica de Catalunya, Barcelona, Spain / J.-J. Pedreno-Manresa, ADVA, Munich, Germany / A. Dochhan, ADVA, Munich, Germany / R. Casellas, Centre Tecnològic Telecomunicacions Catalunya, Castelldefels, Spain / A. Muqaddas, University of Bristol, Bristol, UK / O. Gonzalez de Dios, Telefónica, Madrid, Spain / L. Luque Canto, Telefónica, Madrid, Spain / B. Lent, Qognify GmbH, Bruchsal, Germany / J. E. Lopez de Vergara, Naudit HPCN, Madrid, Spain / S. Lopez-Buedo, Naudit HPCN, Madrid, Spain / F. Moreno, Universidad Politécnica de Cartagena, Cartagena, Spain / P. Pavon, Universidad Politécnica de Cartagena, Cartagena, Spain / M. Ruiz, Universitat Politècnica de Catalunya, Barcelona, Spain / S. K. Patri, ADVA, Munich, Germany / A. Giorgetti, CNIT, Pisa, Italy / F. Cugini, CNIT, Pisa, Italy / A. Sgambelluri, CNIT, Pisa, Italy / R. Nejabati, University of Bristol, Bristol, UK / D. Simeonidou, University of Bristol, Bristol, UK / R.-P. Braun, Deutsche Telekom, Germany / A. Autenrieth, ADVA, Munich, Germany / J.-P. Elbers, ADVA, Munich, Germany / J. K. Fischer, Fraunhofer HHI, Berlin, Germany / R. Freund, Fraunhofer HHI, Berlin, Germany, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

The dichotomy of distributed and centralized control: METRO-HAUL, when control planes collide for 5G networks

  • King, Daniel
  • Farrel, Adrian
  • King, Emiko Nishida
  • Casellas Regi, Ramon
  • Velasco Esteban, Luis Domingo
  • Nejabati, Reza
  • Lord, Andrew
Automating the provisioning of 5G services, deployed over a heterogeneous infrastructure (in terms of domains, technologies, and management platforms), remains a complex task, yet driven by the constant need to provide end-to-end connections at network slices at reducing costs and service deployment time. At the same time, such services are increasingly conceived around interconnected functions and require allocation of computing, storage, and networking resources. The METRO-HAUL 5G research initiative acknowledges the need for automation and strives to develop an orchestration platform for services and resources that extends, integrates, and builds on top of existing approaches, macroscopically adopting Transport Software Defined Networking principles, and leveraging the programmability and open control of Transport SDN., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Dedicated protection with signal overlap in elastic optical networks

  • Cugini, Filippo
  • Ruiz Ramírez, Marc
  • Foggi, Tommaso
  • Velasco Esteban, Luis Domingo
  • Sambo, Nicola
  • Castoldi, Piero
In optical dedicated path protection (1 1), the same optical signal is transmitted along both working and backup paths. Thus, in 1 1, the transmission parameters need to be configured according to the most impaired path, e.g., the backup one. This implies that the working signal is typically served with higher than necessary quality of transmission and occupies larger than necessary spectrum resources, leading to inefficient network resource utilization. In this study, we propose to apply the recently introduced signal overlap technique to improve network efficiency of optical dedicated path protection. The signal overlap technique enables uncorrelated optical signals to be superimposed along the same spectrum resources. It relies on a cancellation detection strategy also exploited in wireless communications and recently applied on coherent optical receivers. In particular, this study summarizes the key aspect and transmission performance of the overlap technique and discusses its implementation complexity. Then, two signal overlap schemes, namely, working signal overlap and working and backup signal overlap are introduced for effective optical dedicated path protection. An integer linear programming (ILP) formulation based on the routing, modulation, and spectrum allocation problem and an efficient heuristic are then presented to effectively assess the performance of the proposed overlap-based 1 1 protection strategy under various topologies and traffic profiles. In the considered simulative scenarios (e.g., network diameters well below a thousand kilometers), results show that the more efficient working and backup signal overlap scheme significantly improves the accepted load of dedicated protection requests., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

BER degradation detection and failure identification in elastic optical networks

  • Vela, Alba P.
  • Ruiz Ramírez, Marc
  • Fresi, Francesco
  • Sambo, Nicola
  • Cugini, Filippo
  • Meloni, Gianluca
  • Poti, Luca
  • Velasco Esteban, Luis Domingo
  • Castoldi, Piero
IEEE Optical connections support virtual links in MPLS-over-optical multilayer networks and therefore, errors in the optical layer impact on the quality of the services deployed on such networks. Monitoring the performance of the physical layer allows verifying the proper working of optical connections, as well as to detect bit error rate (BER) degradation and anticipate connection disruption. In addition, failure identification facilitates localizing the cause of the failure by providing a short list of potential failed elements and enables self-decision making to keep committed service level. In this paper, we analyze several failure causes affecting the quality of optical connections and propose two different algorithms: one focused on detecting significant BER changes in optical connections, named as BANDO, and the other focused on identify the most probable failure pattern, named as LUCIDA. BANDO runs inside the network nodes to accelerate degradation detection and sends a notification to the LUCIDA algorithm running on the centralized controller. Experimental measures were carried out on two different setups to obtain values for BER and received power and used to generate synthetic data used in subsequent simulations. Results show significant improvement anticipating maximum BER violation with small failure identification errors., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Modeling and assessing connectivity services performance in a sandbox domain

  • Ruiz Ramírez, Marc
  • Ruiz Noguera, Mario
  • Tabatabaeimehr, Fatemehsadat
  • Gifré Renom, Lluís
  • López-Buedo, Sergio
  • López de Vergara Méndez, Jorge E.
  • González de Dios, Oscar
  • Velasco Esteban, Luis Domingo
©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., The automation of Network Services (NS) consisting of virtual functions connected through a multilayer packet-over-optical network requires predictable Quality of Service (QoS) performance, measured in terms of throughput and latency, to allow making proactive decisions. QoS is typically guaranteed by overprovisioning capacity dedicated to the NS, which increases costs for customers and network operators, especially when the traffic generated by the users and/or the virtual functions highly varies over the time. This article presents the PILOT methodology for modeling the performance of connectivity services during commissioning testing in terms of throughput and latency. Benefits are double: first, an accurate per-connection model allows operators to better operate their networks and reduce the need for overprovisioning; and second, customers can tune their applications to the performance characteristics of the connectivity. PILOT runs in a sandbox domain and constructs a scenario where an efficient traffic flow simulation environment, based on the CURSA-SQ model, is used to generate large amounts of data for Machine Learning (ML) model training and validation. The simulation scenario is tuned using real measurements of the connection (including throughput and latency) obtained from a set of active probes in the operator network. PILOT has been experimentally validated on a distributed testbed connecting UPC and Telefónica premises., This work was partially supported by the EC through the METRO-HAUL (G.A. nº 761727) project, from the Spanish MINECO/FEDER TWINS (TEC2017-90097-R) and TRÁFICA (TEC2015-69417-C2-1-R) projects and from the Catalan Institution for Research and Advanced Studies., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Supporting time-sensitive and best-effort traffic on a common metro infrastructure

  • Velasco Esteban, Luis Domingo
  • Ruiz Ramírez, Marc
© 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., Considerable research and standardization efforts are being made to support time-sensitive traffic, e.g., generated by applications like Industry 4.0 and 5G fronthaul, on packet networks. This letter focuses on analyzing the impact of conveying time-sensitive traffic in operators’ networks when such traffic is mixed with best-effort traffic. Extensions to a continuous $G/G/1/k$ queue model are proposed to evaluate two different Ethernet technologies, synchronous and asynchronous, supporting time-sensitive flows in terms of their influence on the performance of best-effort traffic. Results highlight pros and cons of those technologies to protect best-effort performance., The research leading to these results has received funding from the European Commission for the H2020-ICT-2016- 2 METRO-HAUL project (G.A. 761727), from the AEI/FEDER TWINS project (TEC2017-90097-R), and from the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Autonomic disaggregated multilayer networking

  • Gifre Renom, Lluís
  • Izquierdo Zaragoza, José Luis
  • Ruiz Ramírez, Marc
  • Velasco Esteban, Luis Domingo
Focused on reducing capital expenditures by opening the data plane to multiple vendors without impacting performance, node disaggregation is attracting the interest of network operators. Although the software-defined networking (SDN) paradigm is key for the control of such networks, the increased complexity of multilayer networks strictly requires monitoring/telemetry and data analytics capabilities to assist in creating and operating self-managed (autonomic) networks. Such autonomicity greatly reduces operational expenditures, while improving network performance. In this context, a monitoring and data analytics (MDA) architecture consisting of centralized data storage with data analytics capabilities, together with a generic node agent for monitoring/telemetry supporting disaggregation, is presented. A YANG data model that allows one to clearly separate responsibilities for monitoring configuration from node configuration is also proposed. The MDA architecture and YANG data models are experimentally demonstrated through three different use cases: i) virtual link creation supported by an optical connection, where monitoring is automatically activated; ii) multilayer self-configuration after bit error rate (BER) degradation detection, where a modulation format adaptation is recommended for the SDN controller to minimize errors (this entails reducing the capacity of both the virtual link and supported multiprotocol label switching-transport profile (MPLS-TP) paths); and iii) optical layer selfhealing, including failure localization at the optical layer to find the cause of BER degradation. A combination of active and passive monitoring procedures allows one to localize the cause of the failure, leading to lightpath rerouting recommendations toward the SDN controller avoiding the failing element(s)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Near real-time estimation of end-to-end performance in converged fixed-mobile networks

  • Bernal Escribano, Álvaro
  • Richart Gutiérrez, Matías Mario
  • Ruiz Ramírez, Marc
  • Castro Casales, Alberto
  • Velasco Esteban, Luis Domingo
© <2019> Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The independent operation of mobile and fixed network segments is one of the main barriers that prevents improving network performance while reducing capital expenditures coming from overprovisioning. In particular, a coordinated dynamic network operation of both network segments is essential to guarantee end-to-end Key Performance Indicators (KPI), on which new network services rely on. To achieve such dynamic operation, accurate estimation of end-to-end KPIs is needed to trigger network reconfiguration before performance degrades. In this paper, we present a methodology to achieve an accurate, scalable, and predictive estimation of end-to-end KPIs with sub-second granularity near real-time in converged fixed-mobile networks. Specifically, we extend our CURSA-SQ methodology for mobile network traffic analysis, to enable converged fixed-mobile network operation. CURSA-SQ combines simulation and machine learning fueled with real network monitoring data. Numerical results validate the accuracy, robustness, and usability of the proposed CURSA-SQ methodology for converged fixed-mobile network scenarios., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

SDN-controlled and orchestrated OPSquare DCN enabling automatic network slicing with differentiated QoS provisioning

  • Xue, Xuwei
  • Wang, Fu
  • Agraz Bujan, Fernando
  • Pagès Cruz, Albert
  • Pan, Bitao
  • Yan, Fulong
  • Guo, Xiaojun
  • Spadaro, Salvatore
  • Calabretta, Nicola
© 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, Optical switching techniques have the potential to enable the optical data center network (DCN) interconnections providing high capacity and fast switching capabilities, overcoming thus the bandwidth and latency bottleneck of present electrical switch-based multi-tiered DCNs. The rapid growth of multi-tenant applications with heterogeneous traffic require specialized quality of service (QoS) in terms of packet loss and latency to the DCN infrastructure. Slicing the DCNs into dedicated pieces according to the deployed applications, differentiated QoS, and high resource utilization can be provided. However, slicing the optical DCNs still needs to be investigated because the Software-defined Networking (SDN) technique is developed for the electrical networks, not fully supporting the properties of the optical network. Additionally, Network Slices (NS) need to be automatically provisioned and reconfigured, to provide flexible slice interconnections in support of the multi-tenant applications to be deployed. In this article, we propose and experimentally assess the automatic and flexible NSs configurations of optical OPSquare DCN controlled and orchestrated by an extended SDN control plane for multi-tenant applications with differentiated QoS provisioning. Optical Flow Control (OFC) protocol has been developed to prevent packet losses at switch sides caused by packet contentions. The extended OpenFlow (OF) protocol of SDN is deployed as well in support of the optical switching characteristics. Based on the collected resource topology of data plane, the optical network slices can be dynamically provisioned and automatically reconfigured by the SDN control plane. Meanwhile, experimental results validate that the priority assignment of application flows supplies dynamic QoS performance to various slices running applications with specific requirements in terms of packet loss and transmission latency. In addition, the capability of exposing traffic statistics information of data plane to SDN control plane enables the implementation of load balancing algorithms further improving the network performance with high QoS. No packet loss and less than 4.8 µs server-to-server latency can be guaranteed for the sliced network with highest priority at a load of 0.5., This work is supported by Olympics project (ESTAR17207) and Metro-Haul project (G.A. 761727)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Learning life cycle to speed up autonomic optical transmission and networking adoption

  • Velasco Esteban, Luis Domingo
  • Shariati, Mohammad Behnam
  • Boitier, Fabien
  • Layec, Patricia
  • Ruiz Ramírez, Marc
Autonomic optical transmission and networking requires machine learning (ML) models to be trained with large datasets. However, the availability of enough real data to produce accurate ML models is rarely ensured since new optical equipment and techniques are continuously being deployed in the network. One option is to generate data from simulations and lab experiments, but such data could not cover the whole features space and would translate into inaccuracies in the ML models. In this paper, we propose an ML-based algorithm life cycle to facilitate ML deployment in real operator networks. The dataset for ML training can be initially populated based on the results from simulations and lab experiments. Once ML models are generated, ML retraining can be performed after inaccuracies are detected to improve their precision. Illustrative numerical results show the benefits of the proposed learning cycle for general use cases. In addition, two specific use cases are proposed and demonstrated that implement different learning strategies: (i) a two-phase strategy performing out-of-field training using data from simulations and lab experiments with generic equipment, followed by an in-field adaptation to support heterogeneous equipment (the accuracy of this strategy is shown for a use case of failure detection and identification), and (ii) in-field retraining, where ML models are retrained after detecting model inaccuracies. Different approaches are analyzed and evaluated for a use case of autonomic transmission, where results show the significant benefits of collective learning., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Knowledge management in optical networks: architecture, methods, and use cases [Invited]

  • Ruiz Ramírez, Marc
  • Tabatabaeimehr, Fatemehsadat
  • Velasco Esteban, Luis Domingo
© [2019 Optical Society of America]. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved., Autonomous network operation realized by means of control loops, where prediction from machine learning (ML) models is used as input to proactively reconfigure individual optical devices or the whole optical network, has been recently proposed to minimize human intervention. A general issue in this approach is the limited accuracy of ML models due to the lack of real data for training the models. Although the training dataset can be complemented with data from lab experiments and simulation, it is probable that once in operation, events not considered during the training phase appear and thus lead to model inaccuracies. A feasible solution is to implement self-learning approaches, where model inaccuracies are used to re-train the models in the field and to spread such data for training models being used for devices of the same type in other nodes in the network. In this paper, we develop the concept of collective self-learning aiming at improving the model’s error convergence time as well as at minimizing the amount of data being shared and stored. To this end, we propose a knowledge management (KM) process and an architecture to support it. Besides knowledge usage, the KM process entails knowledge discovery, knowledge sharing, and knowledge assimilation. Specifically, knowledge sharing and assimilation are based on distributing and combining ML models, so specific methods are proposed for combining models. Two use cases are used to evaluate the proposed KM architecture and methods. Exhaustive simulation results show that model-based KM provides the best error convergence time with reduced data being shared., Peer Reviewed, Postprint (author's final draft)