Skip to main content

INVESTIGACION EN FUTURAS REDES TOTALMENTE OPTIMIZADAS MEDIANTE INTELIGENCIA ARTIFICIAL - A

PID2020-118011GB-C21

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

Resultados relacionados

Resultados totales (Incluyendo duplicados): 42
Encontrada(s) 1 página(s)

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

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

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

Fast traffic engineering by gradient descent with learned differentiable routing

  • Rusek, Krzysztof
  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Cholda, Piotr
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Emerging applications such as the metaverse, telesurgery or cloud computing require increasingly complex operational demands on networks (e.g., ultra-reliable low latency). Likewise, the ever-faster traffic dynamics will demand network control mechanisms that can operate at short timescales (e.g., sub-minute). In this context, Traffic Engineering (TE) is a key component to efficiently control network traffic according to some performance goals (e.g., minimize network congestion).This paper presents Routing By Backprop (RBB), a novel TE method based on Graph Neural Networks (GNN) and differentiable programming. Thanks to its internal GNN model, RBB builds an end-to-end differentiable function of the target TE problem (MinMaxLoad). This enables fast TE optimization via gradient descent. In our evaluation, we show the potential of RBB to optimize OSPF-based routing (˜25% of improvement with respect to default OSPF configurations). Moreover, we test the potential of RBB as an initializer of computationally-intensive TE solvers. The experimental results show promising prospects for accelerating this type of solvers and achieving efficient online TE optimization., This work was supported by the Polish Ministry of Science and Higher Education with the subvention funds of the Faculty of Computer Science, Electronics and Telecommunications of AGH University and by the PL-Grid Infrastructure. Also, this publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Accelerating deep reinforcement learning for digital twin network optimization with evolutionary strategies

  • Güemes Palau, Carlos|||0009-0001-8654-0512
  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Xiao, Shihan
  • Cheng, Xiangle
  • Shi, Xiang
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
The recent growth of emergent network applications (e.g., satellite networks, vehicular networks) is increasing the complexity of managing modern communication networks. As a result, the community proposed the Digital Twin Networks (DTN) as a key enabler of efficient network management. Network operators can leverage the DTN to perform different optimization tasks (e.g., Traffic Engineering, Network Planning).Deep Reinforcement Learning (DRL) showed a high performance when applied to solve network optimization problems. In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior. However, DRL scales poorly with the problem size and complexity. In this paper, we explore the use of Evolutionary Strategies (ES) to train DRL agents for solving a routing optimization problem. The experimental results show that ES achieved a training time speed-up of 128 and 6 for the NSFNET and GEANT2 topologies respectively., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Atom: Neural traffic compression with spatio-temporal graph neural networks

  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Rusek, Krzysztof
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
Storing network traffic data is key to efficient network management; however, it is becoming more challenging and costly due to the ever-increasing data transmission rates, traffic volumes, and connected devices. In this paper, we explore the use of neural architectures for network traffic compression. Specifically, we consider a network scenario with multiple measurement points in a network topology. Such measurements can be interpreted as multiple time series that exhibit spatial and temporal correlations induced by network topology, routing, or user behavior. We present Atom, a neural traffic compression method that leverages spatial and temporal correlations present in network traffic. Atom implements a customized spatio-temporal graph neural network design that effectively exploits both types of correlations simultaneously. The experimental results show that Atom can outperform GZIP’s compression ratios by 50%-65% on three real-world networks., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European UnionNextGeneration EU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, refs. number TSI-063000-2021-3, TSI-063000-2021-38, and TSI-0630002021-52). It has also received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”. This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. It was also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. Krzysztof Rusek was supported by the Polish Ministry of Science and Higher Education with the subvention funds of the Faculty of Computer Science, Electronics and Telecommunications of AGH University of Science and Technology., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

ASTrack: Automatic detection and removal of web tracking code with minimal functionality loss

  • Castell Uroz, Ismael
  • Fukuda, Kensuke
  • Barlet Ros, Pere|||0000-0001-7837-0886
Recent advances in web technologies make it more difficult than ever to detect and block web tracking systems. In this work, we propose ASTrack, a novel approach to web tracking detection and removal. ASTrack uses an abstraction of the code structure based on Abstract Syntax Trees to selectively identify web tracking functionality shared across multiple web services. This new methodology allows us to: (i) effectively detect web tracking code even when using evasion techniques (e.g., obfuscation, minification, or webpackaging); and (ii) safely remove those portions of code related to tracking purposes without affecting the legitimate functionality of the website. Our evaluation with the top 10k most popular Internet domains shows that ASTrack can detect web tracking with high precision (98%), while discovering about 50k tracking code pieces and more than 3,400 new tracking URLs not previously recognized by most popular privacy-preserving tools (e.g., uBlock Origin). Moreover, ASTrack achieved a 36% reduction in functionality loss in comparison with the filter lists, one of the safest options available. Using a novel methodology that combines computer vision and manual inspection, we estimate that full functionality is preserved in more than 97% of the websites., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also par-tially supported by the NII internship program., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Detecting contextual network anomalies with graph neural networks

  • Latif Martínez, Hamid|||0000-0001-6006-3175
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
Detecting anomalies on network traffic is a complex task due to the massive amount of traffic flows in today’s networks, as well as the highly-dynamic nature of traffic over time. In this paper, we propose the use of Graph Neural Networks (GNN) for network traffic anomaly detection. We formulate the problem as contextual anomaly detection on network traffic measurements, and propose a custom GNN-based solution that detects traffic anomalies on origin-destination flows. In our evaluation, we use real-world data from Abilene (6 months), and make a comparison with other widely used methods for the same task (PCA, EWMA, RNN). The results show that the anomalies detected by our solution are quite complementary to those captured by the baselines (with a max. of 36.33% overlapping anomalies for PCA). Moreover, we manually inspect the anomalies detected by our method, and find that a large portion of them can be visually validated by a network expert (64% with high confidence, 18% with mid confidence, 18% normal traffic). Lastly, we analyze the characteristics of the anomalies through two paradigmatic cases that are quite representative of the bulk of anomalies., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/50110-0011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA). This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union – NextGeneration EU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, refs. number TSI-063000-2021-3, TSI-063000-2021-38, and TSI-063000-2021-52). It has also received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Flow optimization at inter-datacenter networks for application run-time acceleration

  • Serracanta Pujol, Berta|||0000-0003-3195-2576
  • Rodríguez Natal, Alberto
  • Maino, Fabio
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
In the present-day, distributed applications are commonly spread across multiple datacenters, reaching out to edge and fog computing locations. The transition away from single datacenter hosting is driven by capacity constraints in datacenters and the adoption of hybrid deployment strategies, combining on-premise and public cloud facilities. However, the performance of such applications is often limited by extended Flow Completion Times (FCT) for short flows due to queuing behind bursts of packets from concurrent long flows. To address this challenge, we propose a solution to prioritize short flows over long flows in the Software-Defined Wide-Area Network (SD-WAN) interconnecting the distributed computing platforms. Our solution utilizes eBPF to segregate short and long flows, transmitting them over separate tunnels with the same properties. By effectively mitigating queuing delays, we consistently achieve a 1.5 times reduction in FCT for short flows, resulting in improved application response times. The proposed solution works with encrypted traffic and is application-agnostic, making it deployable in diverse distributed environments without modifying the applications themselves. Our testbed evaluation demonstrates the effectiveness of our approach in accelerating the run-time of distributed applications, providing valuable insights for optimizing multi-datacenter and edge deployments., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

RouteNet-Erlang: A graph neural network for network performance evaluation

  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Rusek, Krzysztof
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Wu, Bo
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Network modeling is a fundamental tool in network research, design, and operation. Arguably the most popular method for modeling is Queuing Theory (QT). Its main limitation is that it imposes strong assumptions on the packet arrival process, which typically do not hold in real networks. In the field of Deep Learning, Graph Neural Networks (GNN) have emerged as a new technique to build data-driven models that can learn complex and non-linear behavior. In this paper, we present RouteNet-Erlang, a pioneering GNN architecture designed to model computer networks. RouteNet-Erlang supports complex traffic models, multi-queue scheduling policies, routing policies and can provide accurate estimates in networks not seen in the training phase. We benchmark RouteNet-Erlang against a state-of-the-art QT model, and our results show that it outperforms QT in all the network scenarios., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Unveiling the potential of graph neural networks for BGP anomaly detection

  • Latif Martínez, Hamid|||0000-0001-6006-3175
  • Paillissé Vilanova, Jordi|||0000-0001-7733-9713
  • Yang, Jinze
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
The Border Gateway Protocol (BGP) is central to the global connectivity of the Internet, enabling fast and efficient dissemination of routing information. Hence, detecting any anomaly concerning BGP announcements is of critical importance to ensure the continuous operation of Internet services. Typically, BGP anomaly detection algorithms have relied on features of the BGP messages, such as the average length of the AS_PATH attribute, the volume of messages, or the type of message (announcement or withdrawal). Even though these algorithms provide good performance, they do not take into account the BGP topology, that is, the graph of ASes created by the BGP announcements. In this paper we investigate if such topology can be useful to predict BGP anomalies. We leverage Graph Neural Networks (GNN), a subset of the Neural Network (NN) family that is designed to process graph-structured data. We propose a GNN model to detect BGP anomalies and study its generalization capability. We compare its performance with two baseline models: a Support Vector Machine (SVM) and a Multilayer Perceptron (MLP), two Machine Learning (ML) techniques used in state-of-the-art solutions. Our GNN model achieves an accuracy of 79.6% using a weakly supervised dataset of 300 anomalies and is able to outperform the two baseline models., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Detecting and analyzing mouse tracking in the wild

  • Urpí Bricollé, Marcel
  • Castell Uroz, Ismael
  • Barlet Ros, Pere|||0000-0001-7837-0886
Nowadays, most websites collect personal information about their users in order to identify them and personalize their services. Among the tools used to that end, fingerprinting is one of the most advanced and precise methods, given the huge amount of features they can collect and combine to build a robust identifier of the user. Although many fingerprinting techniques have recently been studied in the literature, the use and prevalence of mouse tracking, a method that collects information about the computer pointer, is still unexplored in detail. In this work, we propose a new methodology to detect this tracking method and measure its actual usage on the top 80,000 most popular websites. Our results show that about 1.2% of the analyzed websites use some sort of mouse tracking, including some popular websites within the top-1k ranking., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also supported by the Catalan Institution for Research and Advanced Studies (ICREA Academia)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Application of linear regression in latency estimation in packet-switched 5G xHaul networks

  • Klinkowski, Miroslaw
  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Careglio, Davide|||0000-0002-7931-8147
In this work, we aim at investigating the applicability of machine learning (ML), namely, a linear regression (LR) model for estimation of flows latencies in packet-switched 5G xHaul networks. The analysis is performed in a network scenario in which the switches are connected using high-capacity fiber links., The work was supported by National Science Centre, Poland under Grant No. 2018/31/B/ST7/03456. Moreover, it was also supported by the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Wavelet-enhanced graph neural networks: towards non-parametric network traffic modeling

  • Güemes Palau, Carlos|||0009-0001-8654-0512
  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Paillissé Vilanova, Jordi|||0000-0001-7733-9713
  • López Brescó, Albert|||0009-0005-0611-5516
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Network modeling is crucial for the design, management, and optimization of modern telecommunications and data networks. Recent advancements in Machine Learning (ML), specifically Graph Neural Networks (GNNs), offer promising solutions but rely on parameterized traffic representations, necessitating retraining for new traffic patterns. This paper explores integrating the Discrete Wavelet Transform (DWT) with GNNs to enhance network traffic modeling. By leveraging wavelets, which decompose signals into both time and frequency components, we aim to encode traffic patterns without assuming specific distributions, improving model adaptability and accuracy. We modify the state-of-the-art RouteNet-Fermi model to incorporate wavelet-based traffic encoding and evaluate its performance across different synthetic and real traffic scenarios. Our findings show that wavelet-based encoding handles unseen traffic distributions with minimal impact on performance, unlike traditional parameter-based approaches. This work represents a step forward in bridging the gap between non-parametric traffic representation and advanced network modeling, offering a promising solution for dynamic and complex network environments., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA). Carlos Güemes is funded by the Joan Oró predoctoral program, from the Secretariat for Universities and Research, part of the Ministry of Research and Universities of the Government of Catalonia, and the European Social Fund Plus (ref. BDNS 657443). Jordi Paillisse is funded by NextGen EU, Ministry of Universities and Recovery, Transformation and Resilience Plan, through a call from UPC (Grant Ref. 2022 UPC-MSC-93871)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Evaluation of joint controller placement for latency and reliability-aware control plane

  • Rasol, Kurdman Abdulrahman Rasol
  • Domingo Pascual, Jordi|||0000-0001-6277-7542
The separation of the forwarding and control planes in software-defined networking provides flexibility for network management. The Controller Placement Problem (CPP) is an important issue affecting network performance. This paper presents an evaluation of the Joint Latency and Reliability-Aware Controller Placement (LRCP) optimization model. LRCP provides network administrators with flexible choices to simultaneously achieve a trade-off between the switch-To-controller latency and the controller-To-controller latency, including the reliability aspect using alternative backup paths. Control plane latency (CPL) is used as the evaluation metric and it is defined as the sum of average switch-To-controller latency and the average inter-controller latency. For each optimal placement in the network, the control plane latency using the real latencies of the real network topology is computed. Results from the control plane latency metric show how the number and location of controllers influence the reliability of the network. In the event of a single link failure, the real CPL for LRCP placements is computed and assesses how good the LRCP placements are. The CPL metric is used to compare with other models using latency and reliability metrics., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work has been also partially funded by the Spanish Ministry of Economy and Competitiveness, under contract TEC 2017-90034-C2-1-R (ALLIANCE)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

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

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

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

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

Enhancing 5G radio planning with graph representations and deep learning

  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Suárez Varela, José
  • Lutu, Andra
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
The roll out of new mobile network generations poses hard challenges due to various factors such as cost-benefit tradeoffs, existing infrastructure, and new technology aspects. In particular, one of the main challenges for the 5G deployment lies in optimal 5G radio coverage while accounting for diverse service performance metrics. This paper introduces a Deep Learning-based approach to assist in 5G radio planning by utilizing data from previous-generation cells. Our solution relies on a custom graph representation to leverage the information available from existing cells, and employs a Graph Neural Network (GNN) model to process such data efficiently. In our evaluation, we test its potential to model the transition from 4G to 5G NSA using real-world data from a UK mobile network operator. The experimental results show that our solution achieves high accuracy in predicting key performance indicators in new 5G cells, with a Mean Absolute Percentage Error (MAPE) <17% when evaluated on samples from the same area where it was trained. Moreover, we test its generalization capability over various geographical areas not included in the training, achieving a MAPE <19%. This suggests beneficial properties for achieving robust solutions applicable to 5G planning in new areas without the need of retraining., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/ 501100011033. It was also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. The work was also supported by AEON-ZERO (TSI-063000-2021-52) and AEON-CPS (TSI-063000-2021-38), subprojects of AEON coordinated project, funded by the Ministry of Economic Affairs and Digital Transformation and the European UnionNextGenerationEU/PRTR in the UNICO 5G I+D call. Also, it has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Practical spectral efficiency estimation for optical networking

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

ML-enabled flow admission control policy for proactive QoS assurance in programmable RINA networks

  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Solé Pareta, Josep|||0000-0002-9411-6308
  • Careglio, Davide|||0000-0002-7931-8147
In this paper, we investigate the deployment and performance benefits of a machine learning (ML)-enabled flow admission control policy for programmable networks following the clean slate Recursive InterNetwork Architecture (RINA) design principles. The proposed flow admission control policy is based on RouteNet, a cutting-edge Graph Neural Network (GNN) able to accurately predict per-path packet loss, delay and jitter metrics. Upon arrival of a new flow request, RouteNet can accurately estimate the Quality of Service (QoS) metrics experienced by all active traffic flows if the new incoming one is established in the network. In this way, incoming flow requests are accepted only when the QoS levels of all traffic flows are satisfied appropriately. Throughout the paper, we illustrate our envisioned ML-enabled QoS-aware RINA network scenario, while also disclosing initial proof-of-concept experimental results using the publicly available IRATI RINA prototype., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

FlowDT: A Flow-aware Digital Twin for computer networks

  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Cheng, Xiangle
  • Shi, Xiang
  • Xiao, Shihan
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Network modeling is an essential tool for network planning and management. It allows network administrators to explore the performance of new protocols, mechanisms, or optimal configurations without the need for testing them in real production networks. Recently, Graph Neural Networks (GNNs) have emerged as a practical solution to produce network models that can learn and extract complex patterns from real data without making any assumptions. However, state-of-the-art GNN-based network models only work with traffic matrices, this is a very coarse and simplified representation of network traffic. Although this assumption has shown to work well in certain use-cases, it is a limiting factor because, in practice, networks operate with flows. In this paper, we present FlowDT a new DL-based solution designed to model computer networks at the fine-grained flow level. In our evaluation, we show how FlowDT can accurately predict relevant per-flow performance metrics with an error of 3.5%, FlowDT’s performance is also benchmarked against vanilla DL models as well as with Queuing Theory., This work has been supported by the Spanish Government through project TRAINER-A (PID2020-118011GB-C21) with FEDER contribution and the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

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

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

Real-time generation of 3-dimensional representations of static objects using small unmanned aerial vehicles

  • Talarn Bell-lloch, Pau
  • Ollé Ferrayuoli, Bernat
  • Lemic, Filip
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Costa Pérez, Xavier
Recent advances in robotics and nanotechnology resulted in a set of miniaturized Unmanned Aerial Vehicles (UAVs). Such small UAVs are envisioned to operate in hard-to-reach areas for enabling applications such as structural monitoring or content capturing. Towards showcasing this vision, we demonstrate a small UAV-supported setup for real-time autonomous generation of 3-Dimensional (3D) representations of static objects. In the setup, a small UAV (i.e., CrazyFlie 2.1) is envisioned to visit a set of locations, acting as a carrier and power source of a camera sensor. At each location, the sensor is expected to take a picture of the object and report it to the station. The station implements a pipeline for 3D reconstruction based on the pictures taken by the UAV., This work was funded by the MCIN/AEI/10.13039/01100011033/ FEDER/EU HoloMit 2.0 (PID2021-126551OB-C21) and MCIN/AEI/ 10.13039/501100011033 TRAINER-A (PID2020-118011GB-C21)., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Fast traffic engineering by gradient descent with learned differentiable routing

  • Rusek, Krzysztof
  • Almasan Puscas, Felician Paul
  • Suárez-Varela Maciá, José Rafael
  • Cholda, Piotr
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Emerging applications such as the metaverse, telesurgery or cloud computing require increasingly complex operational demands on networks (e.g., ultra-reliable low latency). Likewise, the ever-faster traffic dynamics will demand network control mechanisms that can operate at short timescales (e.g., sub-minute). In this context, Traffic Engineering (TE) is a key component to efficiently control network traffic according to some performance goals (e.g., minimize network congestion).This paper presents Routing By Backprop (RBB), a novel TE method based on Graph Neural Networks (GNN) and differentiable programming. Thanks to its internal GNN model, RBB builds an end-to-end differentiable function of the target TE problem (MinMaxLoad). This enables fast TE optimization via gradient descent. In our evaluation, we show the potential of RBB to optimize OSPF-based routing (˜25% of improvement with respect to default OSPF configurations). Moreover, we test the potential of RBB as an initializer of computationally-intensive TE solvers. The experimental results show promising prospects for accelerating this type of solvers and achieving efficient online TE optimization., This work was supported by the Polish Ministry of Science and Higher Education with the subvention funds of the Faculty of Computer Science, Electronics and Telecommunications of AGH University and by the PL-Grid Infrastructure. Also, this publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

ML-enabled flow admission control policy for proactive QoS assurance in programmable RINA networks

  • Perelló Muntan, Jordi
  • Solé Pareta, Josep
  • Careglio, Davide
In this paper, we investigate the deployment and performance benefits of a machine learning (ML)-enabled flow admission control policy for programmable networks following the clean slate Recursive InterNetwork Architecture (RINA) design principles. The proposed flow admission control policy is based on RouteNet, a cutting-edge Graph Neural Network (GNN) able to accurately predict per-path packet loss, delay and jitter metrics. Upon arrival of a new flow request, RouteNet can accurately estimate the Quality of Service (QoS) metrics experienced by all active traffic flows if the new incoming one is established in the network. In this way, incoming flow requests are accepted only when the QoS levels of all traffic flows are satisfied appropriately. Throughout the paper, we illustrate our envisioned ML-enabled QoS-aware RINA network scenario, while also disclosing initial proof-of-concept experimental results using the publicly available IRATI RINA prototype., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Flow optimization at inter-datacenter networks for application run-time acceleration

  • Serracanta Pujol, Berta
  • Rodríguez Natal, Alberto
  • Maino, Fabio
  • Cabellos Aparicio, Alberto
In the present-day, distributed applications are commonly spread across multiple datacenters, reaching out to edge and fog computing locations. The transition away from single datacenter hosting is driven by capacity constraints in datacenters and the adoption of hybrid deployment strategies, combining on-premise and public cloud facilities. However, the performance of such applications is often limited by extended Flow Completion Times (FCT) for short flows due to queuing behind bursts of packets from concurrent long flows. To address this challenge, we propose a solution to prioritize short flows over long flows in the Software-Defined Wide-Area Network (SD-WAN) interconnecting the distributed computing platforms. Our solution utilizes eBPF to segregate short and long flows, transmitting them over separate tunnels with the same properties. By effectively mitigating queuing delays, we consistently achieve a 1.5 times reduction in FCT for short flows, resulting in improved application response times. The proposed solution works with encrypted traffic and is application-agnostic, making it deployable in diverse distributed environments without modifying the applications themselves. Our testbed evaluation demonstrates the effectiveness of our approach in accelerating the run-time of distributed applications, providing valuable insights for optimizing multi-datacenter and edge deployments., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Accelerating deep reinforcement learning for digital twin network optimization with evolutionary strategies

  • Güemes Palau, Carlos
  • Almasan Puscas, Felician Paul
  • Xiao, Shihan
  • Cheng, Xiangle
  • Shi, Xiang
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
The recent growth of emergent network applications (e.g., satellite networks, vehicular networks) is increasing the complexity of managing modern communication networks. As a result, the community proposed the Digital Twin Networks (DTN) as a key enabler of efficient network management. Network operators can leverage the DTN to perform different optimization tasks (e.g., Traffic Engineering, Network Planning).Deep Reinforcement Learning (DRL) showed a high performance when applied to solve network optimization problems. In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior. However, DRL scales poorly with the problem size and complexity. In this paper, we explore the use of Evolutionary Strategies (ES) to train DRL agents for solving a routing optimization problem. The experimental results show that ES achieved a training time speed-up of 128 and 6 for the NSFNET and GEANT2 topologies respectively., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Unveiling the potential of graph neural networks for BGP anomaly detection

  • Latif Martínez, Hamid
  • Paillissé Vilanova, Jordi
  • Yang, Jinze
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
The Border Gateway Protocol (BGP) is central to the global connectivity of the Internet, enabling fast and efficient dissemination of routing information. Hence, detecting any anomaly concerning BGP announcements is of critical importance to ensure the continuous operation of Internet services. Typically, BGP anomaly detection algorithms have relied on features of the BGP messages, such as the average length of the AS_PATH attribute, the volume of messages, or the type of message (announcement or withdrawal). Even though these algorithms provide good performance, they do not take into account the BGP topology, that is, the graph of ASes created by the BGP announcements. In this paper we investigate if such topology can be useful to predict BGP anomalies. We leverage Graph Neural Networks (GNN), a subset of the Neural Network (NN) family that is designed to process graph-structured data. We propose a GNN model to detect BGP anomalies and study its generalization capability. We compare its performance with two baseline models: a Support Vector Machine (SVM) and a Multilayer Perceptron (MLP), two Machine Learning (ML) techniques used in state-of-the-art solutions. Our GNN model achieves an accuracy of 79.6% using a weakly supervised dataset of 300 anomalies and is able to outperform the two baseline models., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Wavelet-enhanced graph neural networks: towards non-parametric network traffic modeling

  • Güemes Palau, Carlos
  • Ferriol Galmés, Miquel
  • Paillissé Vilanova, Jordi
  • López Brescó, Albert
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Network modeling is crucial for the design, management, and optimization of modern telecommunications and data networks. Recent advancements in Machine Learning (ML), specifically Graph Neural Networks (GNNs), offer promising solutions but rely on parameterized traffic representations, necessitating retraining for new traffic patterns. This paper explores integrating the Discrete Wavelet Transform (DWT) with GNNs to enhance network traffic modeling. By leveraging wavelets, which decompose signals into both time and frequency components, we aim to encode traffic patterns without assuming specific distributions, improving model adaptability and accuracy. We modify the state-of-the-art RouteNet-Fermi model to incorporate wavelet-based traffic encoding and evaluate its performance across different synthetic and real traffic scenarios. Our findings show that wavelet-based encoding handles unseen traffic distributions with minimal impact on performance, unlike traditional parameter-based approaches. This work represents a step forward in bridging the gap between non-parametric traffic representation and advanced network modeling, offering a promising solution for dynamic and complex network environments., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA). Carlos Güemes is funded by the Joan Oró predoctoral program, from the Secretariat for Universities and Research, part of the Ministry of Research and Universities of the Government of Catalonia, and the European Social Fund Plus (ref. BDNS 657443). Jordi Paillisse is funded by NextGen EU, Ministry of Universities and Recovery, Transformation and Resilience Plan, through a call from UPC (Grant Ref. 2022 UPC-MSC-93871)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Enhancing 5G radio planning with graph representations and deep learning

  • Almasan Puscas, Felician Paul
  • Suárez Varela, José
  • Lutu, Andra
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
The roll out of new mobile network generations poses hard challenges due to various factors such as cost-benefit tradeoffs, existing infrastructure, and new technology aspects. In particular, one of the main challenges for the 5G deployment lies in optimal 5G radio coverage while accounting for diverse service performance metrics. This paper introduces a Deep Learning-based approach to assist in 5G radio planning by utilizing data from previous-generation cells. Our solution relies on a custom graph representation to leverage the information available from existing cells, and employs a Graph Neural Network (GNN) model to process such data efficiently. In our evaluation, we test its potential to model the transition from 4G to 5G NSA using real-world data from a UK mobile network operator. The experimental results show that our solution achieves high accuracy in predicting key performance indicators in new 5G cells, with a Mean Absolute Percentage Error (MAPE) <17% when evaluated on samples from the same area where it was trained. Moreover, we test its generalization capability over various geographical areas not included in the training, achieving a MAPE <19%. This suggests beneficial properties for achieving robust solutions applicable to 5G planning in new areas without the need of retraining., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/ 501100011033. It was also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. The work was also supported by AEON-ZERO (TSI-063000-2021-52) and AEON-CPS (TSI-063000-2021-38), subprojects of AEON coordinated project, funded by the Ministry of Economic Affairs and Digital Transformation and the European UnionNextGenerationEU/PRTR in the UNICO 5G I+D call. Also, it has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Application of linear regression in latency estimation in packet-switched 5G xHaul networks

  • Klinkowski, Miroslaw
  • Perelló Muntan, Jordi
  • Careglio, Davide
In this work, we aim at investigating the applicability of machine learning (ML), namely, a linear regression (LR) model for estimation of flows latencies in packet-switched 5G xHaul networks. The analysis is performed in a network scenario in which the switches are connected using high-capacity fiber links., The work was supported by National Science Centre, Poland under Grant No. 2018/31/B/ST7/03456. Moreover, it was also supported by the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Evaluation of joint controller placement for latency and reliability-aware control plane

  • Rasol, Kurdman Abdulrahman Rasol
  • Domingo Pascual, Jordi
The separation of the forwarding and control planes in software-defined networking provides flexibility for network management. The Controller Placement Problem (CPP) is an important issue affecting network performance. This paper presents an evaluation of the Joint Latency and Reliability-Aware Controller Placement (LRCP) optimization model. LRCP provides network administrators with flexible choices to simultaneously achieve a trade-off between the switch-To-controller latency and the controller-To-controller latency, including the reliability aspect using alternative backup paths. Control plane latency (CPL) is used as the evaluation metric and it is defined as the sum of average switch-To-controller latency and the average inter-controller latency. For each optimal placement in the network, the control plane latency using the real latencies of the real network topology is computed. Results from the control plane latency metric show how the number and location of controllers influence the reliability of the network. In the event of a single link failure, the real CPL for LRCP placements is computed and assesses how good the LRCP placements are. The CPL metric is used to compare with other models using latency and reliability metrics., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. This work has been also partially funded by the Spanish Ministry of Economy and Competitiveness, under contract TEC 2017-90034-C2-1-R (ALLIANCE)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

RouteNet-Erlang: A graph neural network for network performance evaluation

  • Ferriol Galmés, Miquel
  • Rusek, Krzysztof
  • Suárez-Varela Maciá, José Rafael
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Wu, Bo
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Network modeling is a fundamental tool in network research, design, and operation. Arguably the most popular method for modeling is Queuing Theory (QT). Its main limitation is that it imposes strong assumptions on the packet arrival process, which typically do not hold in real networks. In the field of Deep Learning, Graph Neural Networks (GNN) have emerged as a new technique to build data-driven models that can learn complex and non-linear behavior. In this paper, we present RouteNet-Erlang, a pioneering GNN architecture designed to model computer networks. RouteNet-Erlang supports complex traffic models, multi-queue scheduling policies, routing policies and can provide accurate estimates in networks not seen in the training phase. We benchmark RouteNet-Erlang against a state-of-the-art QT model, and our results show that it outperforms QT in all the network scenarios., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Practical spectral efficiency estimation for optical networking

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

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

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

Detecting contextual network anomalies with graph neural networks

  • Latif Martínez, Hamid
  • Suárez-Varela Maciá, José Rafael
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
Detecting anomalies on network traffic is a complex task due to the massive amount of traffic flows in today’s networks, as well as the highly-dynamic nature of traffic over time. In this paper, we propose the use of Graph Neural Networks (GNN) for network traffic anomaly detection. We formulate the problem as contextual anomaly detection on network traffic measurements, and propose a custom GNN-based solution that detects traffic anomalies on origin-destination flows. In our evaluation, we use real-world data from Abilene (6 months), and make a comparison with other widely used methods for the same task (PCA, EWMA, RNN). The results show that the anomalies detected by our solution are quite complementary to those captured by the baselines (with a max. of 36.33% overlapping anomalies for PCA). Moreover, we manually inspect the anomalies detected by our method, and find that a large portion of them can be visually validated by a network expert (64% with high confidence, 18% with mid confidence, 18% normal traffic). Lastly, we analyze the characteristics of the anomalies through two paradigmatic cases that are quite representative of the bulk of anomalies., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/50110-0011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA). This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European Union – NextGeneration EU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, refs. number TSI-063000-2021-3, TSI-063000-2021-38, and TSI-063000-2021-52). It has also received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

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

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

Atom: Neural traffic compression with spatio-temporal graph neural networks

  • Almasan Puscas, Felician Paul
  • Rusek, Krzysztof
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
Storing network traffic data is key to efficient network management; however, it is becoming more challenging and costly due to the ever-increasing data transmission rates, traffic volumes, and connected devices. In this paper, we explore the use of neural architectures for network traffic compression. Specifically, we consider a network scenario with multiple measurement points in a network topology. Such measurements can be interpreted as multiple time series that exhibit spatial and temporal correlations induced by network topology, routing, or user behavior. We present Atom, a neural traffic compression method that leverages spatial and temporal correlations present in network traffic. Atom implements a customized spatio-temporal graph neural network design that effectively exploits both types of correlations simultaneously. The experimental results show that Atom can outperform GZIP’s compression ratios by 50%-65% on three real-world networks., This work was supported by the Spanish Ministry of Economic Affairs and Digital Transformation and the European UnionNextGeneration EU, in the framework of the Recovery Plan, Transformation and Resilience (PRTR) (Call UNICO I+D 5G 2021, refs. number TSI-063000-2021-3, TSI-063000-2021-38, and TSI-0630002021-52). It has also received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”. This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/501100011033. It was also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA) and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. Krzysztof Rusek was supported by the Polish Ministry of Science and Higher Education with the subvention funds of the Faculty of Computer Science, Electronics and Telecommunications of AGH University of Science and Technology., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

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

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

ASTrack: Automatic detection and removal of web tracking code with minimal functionality loss

  • Castell Uroz, Ismael
  • Fukuda, Kensuke
  • Barlet Ros, Pere
Recent advances in web technologies make it more difficult than ever to detect and block web tracking systems. In this work, we propose ASTrack, a novel approach to web tracking detection and removal. ASTrack uses an abstraction of the code structure based on Abstract Syntax Trees to selectively identify web tracking functionality shared across multiple web services. This new methodology allows us to: (i) effectively detect web tracking code even when using evasion techniques (e.g., obfuscation, minification, or webpackaging); and (ii) safely remove those portions of code related to tracking purposes without affecting the legitimate functionality of the website. Our evaluation with the top 10k most popular Internet domains shows that ASTrack can detect web tracking with high precision (98%), while discovering about 50k tracking code pieces and more than 3,400 new tracking URLs not previously recognized by most popular privacy-preserving tools (e.g., uBlock Origin). Moreover, ASTrack achieved a 36% reduction in functionality loss in comparison with the filter lists, one of the safest options available. Using a novel methodology that combines computer vision and manual inspection, we estimate that full functionality is preserved in more than 97% of the websites., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also par-tially supported by the NII internship program., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

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

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

Real-time generation of 3-dimensional representations of static objects using small unmanned aerial vehicles

  • Talarn Bell-lloch, Pau
  • Ollé Ferrayuoli, Bernat
  • Lemic, Filip
  • Abadal Cavallé, Sergi
  • Costa Pérez, Xavier
Recent advances in robotics and nanotechnology resulted in a set of miniaturized Unmanned Aerial Vehicles (UAVs). Such small UAVs are envisioned to operate in hard-to-reach areas for enabling applications such as structural monitoring or content capturing. Towards showcasing this vision, we demonstrate a small UAV-supported setup for real-time autonomous generation of 3-Dimensional (3D) representations of static objects. In the setup, a small UAV (i.e., CrazyFlie 2.1) is envisioned to visit a set of locations, acting as a carrier and power source of a camera sensor. At each location, the sensor is expected to take a picture of the object and report it to the station. The station implements a pipeline for 3D reconstruction based on the pictures taken by the UAV., This work was funded by the MCIN/AEI/10.13039/01100011033/ FEDER/EU HoloMit 2.0 (PID2021-126551OB-C21) and MCIN/AEI/ 10.13039/501100011033 TRAINER-A (PID2020-118011GB-C21)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Detecting and analyzing mouse tracking in the wild

  • Urpí Bricollé, Marcel
  • Castell Uroz, Ismael
  • Barlet Ros, Pere
Nowadays, most websites collect personal information about their users in order to identify them and personalize their services. Among the tools used to that end, fingerprinting is one of the most advanced and precise methods, given the huge amount of features they can collect and combine to build a robust identifier of the user. Although many fingerprinting techniques have recently been studied in the literature, the use and prevalence of mouse tracking, a method that collects information about the computer pointer, is still unexplored in detail. In this work, we propose a new methodology to detect this tracking method and measure its actual usage on the top 80,000 most popular websites. Our results show that about 1.2% of the analyzed websites use some sort of mouse tracking, including some popular websites within the top-1k ranking., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501100011033. This work is also supported by the Catalan Institution for Research and Advanced Studies (ICREA Academia)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

FlowDT: A Flow-aware Digital Twin for computer networks

  • Ferriol Galmés, Miquel
  • Cheng, Xiangle
  • Shi, Xiang
  • Xiao, Shihan
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Network modeling is an essential tool for network planning and management. It allows network administrators to explore the performance of new protocols, mechanisms, or optimal configurations without the need for testing them in real production networks. Recently, Graph Neural Networks (GNNs) have emerged as a practical solution to produce network models that can learn and extract complex patterns from real data without making any assumptions. However, state-of-the-art GNN-based network models only work with traffic matrices, this is a very coarse and simplified representation of network traffic. Although this assumption has shown to work well in certain use-cases, it is a limiting factor because, in practice, networks operate with flows. In this paper, we present FlowDT a new DL-based solution designed to model computer networks at the fine-grained flow level. In our evaluation, we show how FlowDT can accurately predict relevant per-flow performance metrics with an error of 3.5%, FlowDT’s performance is also benchmarked against vanilla DL models as well as with Queuing Theory., This work has been supported by the Spanish Government through project TRAINER-A (PID2020-118011GB-C21) with FEDER contribution and the Catalan Institution for Research and Advanced Studies (ICREA)., Peer Reviewed, Postprint (author's final draft)