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 Artículo científico (JournalArticle)

On the stability of the Kubernetes Horizontal Autoscaler control loop

  • Serracanta Pujol, Berta|||0000-0003-3195-2576
  • Lukács, Andor
  • Rodríguez Natal, Alberto
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Rétvári, Gábor
Kubernetes is a widely used platform for deploying and managing containerized applications due to its efficient elastic capabilities. The Horizontal Pod Autoscaler (HPA) in Kubernetes independently adjusts the number of pods for each service, yet these services often operate in an interconnected manner. This study aims to understand the effects of autoscaling events on a graph of interconnected services. To achieve this, we apply control theory to model the HPA’s behavior. We analyze the stability of this model, perform numerical simulations, and deploy a real testbed to evaluate the performance. Our findings demonstrate that the control theory-based model accurately predicts the HPA’s behavior, ensuring system stability with CPU utilization meeting desired thresholds and no traffic loss after a transitional period. The model provides insights into optimizing resource scheduling and improving application performance in Kubernetes environments. Additionally, we extend our model to the whole service graph to understand how individual scaling decisions influence the complex graphs of cloud applications., This work was supported in part by the Spanish I+D+i Project TowaRds fully AI-empowered NetwoRks, subproject A (TRAINER-A), funded by Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 under Grant PID2020-118011GB-C21; in part by the Catalan Institution for Research and Advanced Studies (ICREA) through the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia; in part by the European Social Fund; and in part by the National Research, Development and Innovation Fund of Hungary under Grant OTKA/ANN-135606, Grant OTKA/FK-135074, and Grant OTKA/FK-134604., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

TrackSign-labeled web tracking dataset

  • Castell Uroz, Ismael
  • Barlet Ros, Pere|||0000-0001-7837-0886
Recent studies show that more than 95% of the websites available on the Internet contain at least one of the so-called web tracking systems. These systems are specialized in identifying their users by means of a plethora of different methods. Some of them (e.g., cookies) are very well known by most Internet users. However, the percentage of websites including more "obscure" and privacy-threatening systems, such as fingerprinting methods identifying a user's computer, is constantly increasing. Detecting those methods on today's Internet is very difficult, as almost any website modifies its content dynamically and minimizes its code in order to speed up loading times. This minimization and dynamicity render the website code unreadable by humans. Thus, the research community is constantly looking for new ways to discover unknown web tracking systems running under the hood. In this paper, we present a new dataset containing tracking information for more than 76 million URLs and 45 million online resources, extracted from 1.5 million popular websites. The tracking labeling process was done using a state-of-the-art discovery web tracking algorithm called TrackSign. The dataset also contains information about online security and the relation between the domains, the loaded URLs, and the online resource behind each URL. This information can be useful for different kinds of experiments, such as locating privacy-threatening resources, identifying security threats, or determining characteristics of the URL network graph., 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 Artículo científico (JournalArticle)

Evaluating a multidisciplinary model for managing human uncertainty in 5G cyber-physical-social systems

  • Alzate Mejía, Nestor
  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Santos Boada, Germán|||0000-0002-9528-2287
  • Almeida Amazonas, José Roberto de
This paper presents a comprehensive evaluation of the previously introduced multidisciplinary model to quantify human uncertainty (MMtQHU) within a realistic 5G-enabled cyber–physical–social systems (CPSS) environment. The MMtQHU, which integrates human, social, and environmental factors into CPSS modeling, is applied to the Ingolstadt traffic scenario (InTAS), a detailed urban simulation reflecting high-traffic conditions. By modeling unpredictable driver behaviors, such as deviations from optimal routes, the study assesses the model’s effectiveness in managing human-induced uncertainties in vehicle-for-hire (VFH) applications. The evaluation shows that human uncertainty significantly impacts 5G network resource allocation and traffic dynamics. A comparative analysis of traditional resource allocation methods reveals their limitations in handling the dynamic nature of human behavior. These findings underscore the necessity for advanced, adaptive strategies, potentially leveraging artificial intelligence and machine learning to enhance the resilience and efficiency of 5G networks in CPSS environments. The study offers valuable insights for future advancements in robust and adaptive 5G infrastructure by highlighting the critical role of integrating human behavior into CPSS models., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GBC21) funded by MCIN/AEI/10.13039/501100011033 and by the aid granted by the Sinfoni project of the Cooperative University of Colombia., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

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

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

ENERO: Efficient real-time WAN routing optimization with Deep Reinforcement Learning

  • 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
Wide Area Networks (WAN) are a key infrastructure in today’s society. During the last years, WANs have seen a considerable increase in network’s traffic and network applications, imposing new requirements on existing network technologies (e.g., low latency and high throughput). Consequently, Internet Service Providers (ISP) are under pressure to ensure the customer’s Quality of Service and fulfill Service Level Agreements. Network operators leverage Traffic Engineering (TE) techniques to efficiently manage the network’s resources. However, WAN’s traffic can drastically change during time and the connectivity can be affected due to external factors (e.g., link failures). Therefore, TE solutions must be able to adapt to dynamic scenarios in real-time. In this paper we propose Enero, an efficient real-time TE solution based on a two-stage optimization process. In the first one, Enero leverages Deep Reinforcement Learning (DRL) to optimize the routing configuration by generating a long-term TE strategy. To enable efficient operation over dynamic network scenarios (e.g., when link failures occur), we integrated a Graph Neural Network into the DRL agent. In the second stage, Enero uses a Local Search algorithm to improve DRL’s solution without adding computational overhead to the optimization process. The experimental results indicate that Enero is able to operate in real-world dynamic network topologies in 4.5 s on average for topologies up to 100 links., 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 Artículo científico (JournalArticle)

A multidisciplinary model to quantify human uncertainty in human-centric cyber-physical-social systems: A 5G application use case

  • Alzate Mejía, Nestor
  • Perelló Muntan, Jordi|||0000-0001-6563-2664
  • Santos Boada, Germán|||0000-0002-9528-2287
  • Almeida Amazonas, José Roberto de
The emerging Human-Centric Networks (HCN) paradigm shifts the passive role of individuals to an active one, intertwining the uncertainty of network resource usage with human dynamics, which are difficult to analyze and predict. This phenomenon implies an increase in reciprocal interactions between Cyber-Physical-Social Systems (CPSS) and human activities, presenting the challenge of efficiently allocating network resources while taking into account qualitative human uncertainty. In this study, we propose a conceptual model that addresses and quantifies such uncertainties. The proposed model is characterized by its adaptability to various CPSS applications, facilitating its integration into existing applications and future innovations. The adaptability of the model is based on the application of the sociological concept of Boundary Objects (BO), which allows for the structuring of system components and the generation of a reference architecture that facilitates systematic problem solving. To evaluate the model, we propose a use case related to a Vehicle for Hire (VFH) application operating within a 5G network slice. The integration of the proposed model with the OMNET++ simulation framework has allowed to demonstrate the effectiveness of the model in intricate computational environments and have shown its capacity to incorporate previously overlooked elements that are essential for the optimal allocation of resources in CPSS. This study proposes a methodology for comprehending and mitigating the consequences of human uncertainty, emphasizing the significance of a multidisciplinary approach to resource allocation in sophisticated technological systems., This work was supported in part by the Spanish I+D+i Project TRAINER-A, funded by Ministerio de Ciencia, Innovación y Universidades (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part by the aid granted by the Sinfoni Project INV3164 of the Cooperative University of Colombia., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

ePrivo.eu: An online service for automatic web tracking discovery

  • Castell Uroz, Ismael
  • Douha Prieto, Ismael
  • Basart Dotras, Meritxell
  • Mesegué Molina, Pol
  • Barlet Ros, Pere|||0000-0001-7837-0886
Given the pervasiveness of web tracking practices on the Internet, many countries are developing and enforcing new privacy regulations to ensure the rights of their citizens. However, discovering websites that do not comply with those regulations is becoming very challenging, given the dynamic nature of the web or the use of obfuscation techniques. This work presents ePrivo, a new online service that can help Internet users, website owners, and regulators inspect how privacy-friendly a given website is. The system explores all the content of the website, including traffic from third parties and dynamically modified content. The ePrivo service combines different state-of-the-art tracking detection and classification methods, including TrackSign, to discover both previously known and zero-day tracking methods. After 6 months of service, ePrivo detected the largest browsing history trackers and more than 40k domains including cookies with a lifespan longer than one year, which is forbidden in some countries., This work was supported in part by the Spanish I+D+i Project TRAINER-A, funded by MCIN/AEI/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part by the Catalan Institution for Research and Advanced Studies (ICREA Academia)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Toward deep application-network integration: architectures, progress and opportunities

  • Serracanta Pujol, Berta|||0000-0003-3195-2576
  • Gao, Kai
  • Ros Giralt, Jordi
  • Rodríguez Natal, Alberto
  • Contreras Murillo, Luis Miguel
  • Yang, Richard
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
With the rise of a new generation of applications (e.g., virtual and augmented reality, artificial intelligence, etc.) demanding stringent performance requirements, the need for networking solutions and architectures that can enable a higher quality of experience (QoE) has become increasingly important. While jointly optimizing application and network may increase the applications' QoE and simultaneously improve the utilization of network resources, such a paradigm has had limited success in real production networks. However, with the combination of revolutionary trends in computer processing demands, networking capabilities, and sustainable business models, it is high time the community explores the full potential of deeper integration between application and network. In this tutorial article, recent trends observed over the past few years are systematically reviewed. These include the paradigm shift in modern communication services toward computing-driven applications, such as on-site AI training, advances in programmable network technologies like software defined networking (SDN), and new business models incentivizing collaboration and cooperation between parties. Following this, successful scenarios that benefit from various forms of deeper network-application integration are reported, highlighting their considerable potential. A unified framework is then introduced, providing an overview of possible architecture paradigms for network-application integration and bringing awareness to existing abstractions, mechanisms, tools, and their potential combinations. The article concludes with a discussion of several remaining challenges in building practical network-application integrated systems., 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 Artículo científico (JournalArticle)

GAT-AD: Graph Attention Networks for contextual anomaly detection in network monitoring

  • Latif Martínez, Hamid|||0000-0001-6006-3175
  • Suárez Varela, José
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
Network anomaly detection is essential to promptly detect and fix issues in the network. Particularly, detecting traffic anomalies enables the early detection of configuration errors, malicious activities, or equipment malfunctions that could lead to severe impact on the network. In this paper, we present GAT-AD, a Deep Learning-based anomaly detection solution for network monitoring systems, which integrates a custom neural network model based on Graph Attention Networks (GAT). Our solution monitors aggregated traffic on origin–destination flows and automatically defines contexts that group flows with similar past activity. The neural network model within GAT-AD can be efficiently trained in a self-supervised manner. We evaluate our solution against two state-of-the-art anomaly detection baselines also based on graph representations and Deep Learning, in two different datasets: (i) WaDi, which is a well-known dataset for anomaly detection in a distributed sensor network, and (ii) Abilene, where we inject synthetically-generated anomalies into a dataset with real-world traffic from a large-scale backbone network. The results show that GAT-AD outperforms the two anomaly detection baselines: in WaDi by 14.1% in recall and 10.07% in F1-score, and in the Abilene dataset by ˜ 17.5% recall with respect to the best baseline., 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), Spain. This work was also supported by the CHISTERA grant CHIST-ERA-22-SPiDDS-02 corresponding to the GRAPHS4SEC project (reference no PCI2023-145974-2) funded by the Agencia Estatal de Investigación, Spain through the PCI 2023 call. This work was also 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). This work was partially supported by the ORIGAMI project, funded by the Smart Networks and Services Joint Undertaking (SNS JU), Spain under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 101139270., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Demystifying content-blockers: Measuring their impact on performance and quality of experience

  • Castell Uroz, Ismael
  • Sánz García, Rubén
  • Solé Pareta, Josep|||0000-0002-9411-6308
  • Barlet Ros, Pere|||0000-0001-7837-0886
With the evolution of the online advertisement and tracking ecosystem, content-blockers have become the reference tool for improving the security, privacy and browsing experience when surfing the Internet. It is also commonly believed that using content-blockers to stop unsolicited content decreases the time needed for loading websites. In this work, we perform a large-scale study on the actual improvements of using content-blockers in terms of performance and quality of experience. For measuring it, we analyze the page size and loading times of the 100K most popular websites, as well as the most relevant QoE metrics, such as the Speed Index, Time to Interactive or the Cumulative Layout Shift, for the subset of the top 10K of them. Our experiments show that using content-blockers results in small improvements in terms of performance. However, contrary to popular belief, this has a negligible impact in terms of loading time and quality of experience. Moreover, in the case of small and lightweight websites, the overhead introduced by content-blockers can even result in decreased performance. Finally, we evaluate the improvement in terms of QoE based on the Mean Opinion Score (MOS) and find that two of the three studied content-blockers present an overall decrease between 3% and 5% instead of the expected improvement., 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 Artículo científico (JournalArticle)

Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case

  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Rusek, Krzysztof
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Deep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve many relevant optimization problems (e.g., routing) in self-driving networks. However, existing DRL-based solutions applied to networking fail to generalize, which means that they are not able to operate properly when applied to network topologies not observed during training. This lack of generalization capability significantly hinders the deployment of DRL technologies in production networks. This is because state-of-the-art DRL-based networking solutions use standard neural networks (e.g., fully connected, convolutional), which are not suited to learn from information structured as graphs. In this paper, we integrate Graph Neural Networks (GNN) into DRL agents and we design a problem specific action space to enable generalization. GNNs are Deep Learning models inherently designed to generalize over graphs of different sizes and structures. This allows the proposed GNN-based DRL agent to learn and generalize over arbitrary network topologies. We test our DRL+GNN agent in a routing optimization use case in optical networks and evaluate it on 180 and 232 unseen synthetic and real-world network topologies respectively. The results show that the DRL+GNN agent is able to outperform state-of-the-art solutions in topologies never seen during training., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501- 100011033. 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. This work was also 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., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

MAGNNETO: A graph neural network-based multi-agent system for traffic engineering

  • Bernárdez Gil, Guillermo
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • López Brescó, Albert|||0009-0005-0611-5516
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Current trends in networking propose the use of Machine Learning (ML) for a wide variety of network optimization tasks. As such, many efforts have been made to produce ML-based solutions for Traffic Engineering (TE), which is a fundamental problem in Internet Service Provider (ISP) networks. Nowadays, state-of-the-art TE optimizers rely on traditional optimization techniques, such as Local search, Constraint Programming, or Linear programming. In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization. MAGNNETO deploys a set of agents across the network that learn and communicate in a distributed fashion via message exchanges between neighboring agents. Particularly, we apply this framework to optimize link weights in Open Shortest Path First (OSPF), with the goal of minimizing network congestion. In our evaluation, we compare MAGNNETO against several state-of-the-art TE optimizers in more than 75 topologies (up to 153 nodes and 354 links), including realistic traffic loads. Our experimental results show that, thanks to its distributed nature, MAGNNETO achieves comparable performance to state-of-the-art TE optimizers with significantly lower execution times. Moreover, our ML-based solution demonstrates a strong generalization capability to successfully operate in new networks unseen during training., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GBC21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), 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 Artículo científico (JournalArticle)

RouteNet-Fermi: network modeling with graph neural networks

  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Paillissé Vilanova, Jordi|||0000-0001-7733-9713
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Rusek, Krzysztof
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complexity, some models present limitations, such as the assumption of Markovian traffic in queuing theory models, or the high computational cost of network simulators. Recent advances in machine learning, such as Graph Neural Networks (GNN), are enabling a new generation of network models that are data-driven and can learn complex non-linear behaviors. In this paper, we present RouteNet-Fermi, a custom GNN model that shares the same goals as Queuing Theory, while being considerably more accurate in the presence of realistic traffic models. The proposed model predicts accurately the delay, jitter, and packet loss of a network. We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles — e.g., with complex non-Markovian models — and arbitrary routing and queue scheduling configurations. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators and scales accurately to larger networks. Our model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset of 1,000 samples, including network topologies one order of magnitude larger than those seen during training. Finally, we have also evaluated RouteNet-Fermi with measurements from a physical testbed and packet traces from a real-life network., This work was supported in part by the Spanish I+D+i Project TRAINER-A funded by the Ministry of Science and Innovation (MCIN)/State Investigation Agency (AEI)/10.13039/501100011033 under Grant PID2020-118011GB-C21, in part by the Catalan Institution for Research and Advanced Studies (ICREA), and in part by 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 Artículo científico (JournalArticle)

Early detection of new web tracking methods across 1.5 million sites

  • Castell Uroz, Ismael
  • Sánchez de Mingo, Óscar
  • Barlet Ros, Pere|||0000-0001-7837-0886
Current web tracking practices pose a constant threat to the privacy of Internet users. As a result, the research community has recently proposed different tools to combat well-known tracking methods. However, the early detection of new, previously unseen tracking systems is still an open research problem. In this paper, we present TrackSign+, a novel approach to discovering new web tracking methods. The main idea behind TrackSign+ is the use of code fingerprinting to identify common pieces of code shared across multiple domains. To detect tracking fingerprints, TrackSign+ builds a novel 4-mode network graph that captures the relationship between domains, URLs, online resources, and code fingerprints. We evaluated TrackSign+ with the 1.5M most popular Internet domains, including more than 45M web resources from almost 77M HTTP requests. Our results show that our method can detect new web tracking resources with high precision (over 92%). TrackSign+ was able to detect more than 300k new trackers, 800k new tracking resources, and 4.5M new tracking URLs, not yet detected by most popular pattern lists at the time. Finally, we also validated the effectiveness of TrackSign+ with more than 20 years of historical data from the Internet Archive., 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 Artículo científico (JournalArticle)

Network digital twin: context, enabling technologies, and opportunities

  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Paillissé Vilanova, Jordi|||0000-0001-7733-9713
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Perino, Diego
  • Lopez, Diego
  • Pastor Perales, Antonio Agustín
  • Harvey, Paul
  • Ciavaglia, Laurent
  • Wong, Leon
  • Xiao, Shihan
  • Ram, Vishnu
  • Shi, Xiang
  • Cheng, Xiangle
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
The proliferation of emergent network applications (e.g., telesurgery, metaverse) is increasing the difficulty of managing modern communication networks. These applications entail stringent network requirements (e.g., ultra-low deterministic latency), which hinders network operators to manage their resources efficiently. In this article, we introduce the network digital twin (NDT), a renovated concept of classical network modeling tools whose goal is to build accurate data-driven network models that can operate in real-time. We describe the general architecture of the NDT and argue that modern machine learning (ML) technologies enable building some of its core components. Then, we present a case study that leverages a ML-based NDT for network performance evaluation and apply it to routing optimization in a QoS-aware use case. Lastly, we describe some key open challenges and research opportunities yet to be explored to achieve effective deployment of NDTs in real-world networks., 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 Artículo científico (JournalArticle)

Graph neural networks for communication networks: context, use cases and opportunities

  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Almasan Puscas, Felician Paul|||0000-0003-3903-6759
  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Rusek, Krzysztof
  • Geyer, Fabien
  • Cheng, Xiangle
  • Shi, Xiang
  • Xiao, Shihan
  • Scarselli, Franco
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Barlet Ros, Pere|||0000-0001-7837-0886
Graph neural networks (GNN) have shown outstanding applications in fields where data is essentially represented as graphs (e.g., chemistry, biology, recommendation systems). In this vein, communication networks comprise many fundamental components that are naturally represented in a graph-structured manner (e.g., topology, routing, signal interference). This position article presents GNNs as a fundamental tool for modeling, control and management of communication networks. GNNs represent a new generation of data-driven models that can accurately learn and reproduce the complex behaviors behind real-world networks. As a result, these models can be applied to a wide variety of networking use cases, such as planning, online optimization, or troubleshooting. The main advantage of GNNs over traditional neural networks lies in their unprecedented generalization capabilities when applied to other networks and configurations unseen during training. This is a critical feature for achieving practical data-driven solutions for networking. This article starts with a brief tutorial on GNNs and some potential applications to communication networks. Then, it presents two state-of-the-art GNN models respectively applied to wired and wireless networks. Lastly, it delves into the key open challenges and opportunities yet to be explored in this novel research area., 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 Artículo científico (JournalArticle)

A one-pass clustering based sketch method for network monitoring

  • Fu, Yongquan
  • An, Lun
  • Shen, Siqi
  • Chen, Kai
  • Barlet Ros, Pere|||0000-0001-7837-0886
Network monitoring solutions need to cope with increasing network traffic volumes, as a result, sketch-based monitoring methods have been extensively studied to trade accuracy for memory scalability and storage reduction. However, sketches are sensitive to skewness in network flow distributions due to hash collisions, and need complicated performance optimization to adapt to line-rate packet streams. We provide Jellyfish, an efficient sketch method that performs one-pass clustering over the network stream. One-pass clustering is realized by adapting the monitoring granularity from the whole network flow to fragments called subflows, which not only reduces the ingestion rate but also provides an efficient intermediate representation for the input to the sketch. Jellyfish provides the network-flow level query interface by reconstructing the network-flow level counters by merging subflow records from the same network flow. We provide probabilistic analysis of the expected accuracy of both existing sketch methods and Jellyfish. Real-world trace-driven experiments show that Jellyfish reduces the average estimation errors by up to six orders of magnitude for per-flow queries, by six orders of magnitude for entropy queries, and up to ten times for heavy-hitter queries., This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 61972409; in part by Hong Kong Research Grants Council (RGC) under Grant TRS T41-603/20-R, Grant GRF-16213621, and Grant ITF ACCESS; in part by the Spanish I+D+i project TRAINER-A, funded by MCIN/AEI/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part by the Catalan Institution for Research and Advanced Studies (ICREA Academia)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Verification of performance degradation in a telecommunications system due to the uncertainty of human users in the loop

  • Alzate Mejía, Nestor
  • Santos Boada, Germán|||0000-0002-9528-2287
  • Almeida Amazonas, José Roberto de
The intensive use of new technologies that cause more interactions between systems and the daily activities of human users is changing the focus on how network re- sources should be managed. However, these changes can create challenges related to the level of uncertainty that people introduce to the system. In this context, this research study seeks to determine whether people’s uncertainty influences network performance and how significant its impact is. For these purposes, a simulated case study of a Vehicle for Hire application designed to run over a network slicing of a fifth-generation (5G) network. The simulations compared call drop rates in several settings configured to represent different levels of uncertainty, introducing random alterations to free channel planning reserved for the handover process. The simulation results reveal that the uncertainty specifically introduced by people exerts a high negative impact on network performance, evidencing the need to develop an algorithm that considers this uncertainty when managing resources within the 5G network core., This work has been supported by the Spanish Government through project TRAINER-A (PID2020-118011GB-C21) with FEDER contribution. Moreover, it has been supported by the Spanish Thematic Network under contract RED2018-102585-T (Go2Edge) and by the aid granted by the Sinfoni project INV2733 of the Cooperative University of Colombia., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Building a Digital Twin for network optimization using graph neural networks

  • Ferriol Galmés, Miquel|||0000-0002-7806-2979
  • Suárez-Varela Maciá, José Rafael|||0000-0002-7141-3414
  • Paillissé Vilanova, Jordi|||0000-0001-7733-9713
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Network modeling is a critical component of Quality of Service (QoS) optimization. Current networks implement Service Level Agreements (SLA) by careful configuration of both routing and queue scheduling policies. However, existing modeling techniques are not able to produce accurate estimates of relevant SLA metrics, such as delay or jitter, in networks with complex QoS-aware queueing policies (e.g., strict priority, Weighted Fair Queueing, Deficit Round Robin). Recently, Graph Neural Networks (GNNs) have become a powerful tool to model networks since they are specifically designed to work with graph-structured data. In this paper, we propose a GNN-based network model able to understand the complex relationship between the queueing policy (scheduling algorithm and queue sizes), the network topology, the routing configuration, and the input traffic matrix. We call our model TwinNet, a Digital Twin that can accurately estimate relevant SLA metrics for network optimization. TwinNet can generalize to its input parameters, operating successfully in topologies, routing, and queueing configurations never seen during training. We evaluate TwinNet over a wide variety of scenarios with synthetic traffic and validate it with real traffic traces. Our results show that TwinNet can provide accurate estimates of end-to-end path delays in 106 unseen real-world topologies, under different queuing configurations with a Mean Absolute Percentage Error (MAPE) of 3.8%, as well as a MAPE of 6.3% error when evaluated with a real testbed. We also showcase the potential of the proposed model for SLA-driven network optimization and what-if analysis., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/, Spain10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), Spain and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia, Spain and the European Social Fund., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Graphene-based wireless agile interconnects for massive heterogeneous multi-chip processors

  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Guirado Liñan, Robert
  • Taghvaee, Hamidreza|||0000-0001-8732-6086
  • Jain, Akshay|||0000-0002-6986-2720
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Saeed, Mohamed
  • Negra, Renato
  • Wang, Zhenxing
  • Wang, Kun-Ta
The main design principles in computer architecture have recently shifted from a monolithic scaling-driven approach to the development of heterogeneous architectures that tightly co-integrate multiple specialized processor and memory chiplets. In such data-hungry multi-chip architectures, current Networks-in-Package (NiPs) may not be enough to cater to their heterogeneous and fast-changing communication demands. This position article makes the case for wireless in-package networking as the enabler of efficient and versatile wired-wireless interconnect fabrics for massive heterogeneous processors. To that end, the use of graphene-based antennas and transceivers with unique frequency-beam reconfigurability in the terahertz band is proposed. The feasibility of such a wireless vision and the main research challenges toward its realization are analyzed from the technological, communications, and computer architecture perspectives., 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 supported by the European Commission under H2020 grants WiPLASH (GA 863337), 2D-EPL (GA 952792), and Graphene Flagship (GA 881603); the FLAGERA framework under grant TUGRACO (HA 3022/9-1, LE 2440/3-1), the European Research Council under grants WINC (GA 101042080), COMPUSAPIEN (GA 725657), and PROJESTOR (GA 682675), the German Ministry of Education and Research under grant GIMMIK (03XP0210) and the and the German Research Foundation under grant HIPEDI (WA 4139/1-1)., Peer Reviewed, Article signat per 21 autors/es: Sergi Abadal, Robert Guirado, Hamidreza Taghvaee, and Akshay Jain are with the Universitat Politècnica de Catalunya, Spain; Elana Pereira de Santana and Peter Haring Bolívar are with the University of Siegen, Germany; Mohamed Saeed, Renato Negra, Kun-Ta Wang, and Max C. Lemme are with RWTH Aachen University, Germany. Zhenxing Wang, Kun-Ta Wang, and Max C. Lemme are also with AMO GmbH, Germany; Joshua Klein, Marina Zapater, Alexandre Levisse, and David Atienza are with the Swiss Federal Institute of Technology, Switzerland. Marina Zapater is also with the University of Applied Sciences and Arts Western Switzerland; Davide Rossi and Francesco Conti are with the University of Bologna,Italy; Martino Dazzi, Geethan Karunaratne, Irem Boybat, and Abu Sebastian are with IBM Research Europe, Switzerland
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

GraphCC: a practical graph learning-based approach to congestion control in datacenters

  • Bernárdez Gil, Guillermo
  • Suárez Varela, José
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere|||0000-0001-7837-0886
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
Congestion Control (CC) plays a fundamental role in optimizing traffic in Datacenter Networks (DCNs). Currently, DCNs implement two main CC protocols: DCTCP and DCQCN. Both protocols are based on Explicit Congestion Notification (ECN), where switches mark packets when they detect congestion. Nowadays, network experts carefully set ECN parameters to optimize the average network performance. However, today’s DCNs experience rapid and abrupt changes that severely affect the network state (e.g., dynamic workloads, incasts), which leads to under-utilization and sub-optimal performance. In this paper we present GraphCC, a framework for in-network CC optimization. GraphCC relies on Multi-agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN), and is compatible with widely deployed ECN-based CC protocols. The proposed solution deploys distributed agents on switches that communicate with their neighbors to cooperate and optimize the global ECN configuration. In our evaluation, we test GraphCC with three real-world traffic workloads, focusing on its capability to accommodate scenarios unseen during training (e.g., traffic changes, failures). We compare GraphCC with a state-of-the-art MARL solution for ECN tuning, and observe that our method outperforms the state-of-the-art baseline in all evaluation scenarios, with improvements up to 20% in average Flow Completion Time, similar mean throughput (within 1%), and significant reductions in buffer occupancy (38.0-85.7%)., This publication is part of the Spanish I+D+i project TRAINER-A (reference PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/ 501100011033, and the research has been partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia, and the European Social Fund. This work is also partially supported by the ORIGAMI project, funded by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 101139270, as well as by the CHISTERA grant CHIST-ERA-22-SPiDDS-02 corresponding to the GRAPHS4SEC project (reference PCI2023-145974-2), funded by the Agencia Estatal de Investigación through the PCI 2023 call., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Graphene-based wireless agile interconnects for massive heterogeneous multi-chip processors

  • Abadal Cavallé, Sergi
  • Guirado Liñan, Robert
  • Taghvaee, Hamidreza
  • Jain, Akshay
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Saeed, Mohamed
  • Negra, Renato
  • Wang, Zhenxing
  • Wang, Kun-Ta
The main design principles in computer architecture have recently shifted from a monolithic scaling-driven approach to the development of heterogeneous architectures that tightly co-integrate multiple specialized processor and memory chiplets. In such data-hungry multi-chip architectures, current Networks-in-Package (NiPs) may not be enough to cater to their heterogeneous and fast-changing communication demands. This position article makes the case for wireless in-package networking as the enabler of efficient and versatile wired-wireless interconnect fabrics for massive heterogeneous processors. To that end, the use of graphene-based antennas and transceivers with unique frequency-beam reconfigurability in the terahertz band is proposed. The feasibility of such a wireless vision and the main research challenges toward its realization are analyzed from the technological, communications, and computer architecture perspectives., 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 supported by the European Commission under H2020 grants WiPLASH (GA 863337), 2D-EPL (GA 952792), and Graphene Flagship (GA 881603); the FLAGERA framework under grant TUGRACO (HA 3022/9-1, LE 2440/3-1), the European Research Council under grants WINC (GA 101042080), COMPUSAPIEN (GA 725657), and PROJESTOR (GA 682675), the German Ministry of Education and Research under grant GIMMIK (03XP0210) and the and the German Research Foundation under grant HIPEDI (WA 4139/1-1)., Peer Reviewed, Article signat per 21 autors/es: Sergi Abadal, Robert Guirado, Hamidreza Taghvaee, and Akshay Jain are with the Universitat Politècnica de Catalunya, Spain; Elana Pereira de Santana and Peter Haring Bolívar are with the University of Siegen, Germany; Mohamed Saeed, Renato Negra, Kun-Ta Wang, and Max C. Lemme are with RWTH Aachen University, Germany. Zhenxing Wang, Kun-Ta Wang, and Max C. Lemme are also with AMO GmbH, Germany; Joshua Klein, Marina Zapater, Alexandre Levisse, and David Atienza are with the Swiss Federal Institute of Technology, Switzerland. Marina Zapater is also with the University of Applied Sciences and Arts Western Switzerland; Davide Rossi and Francesco Conti are with the University of Bologna,Italy; Martino Dazzi, Geethan Karunaratne, Irem Boybat, and Abu Sebastian are with IBM Research Europe, Switzerland, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Graph neural networks for communication networks: context, use cases and opportunities

  • Suárez-Varela Maciá, José Rafael
  • Almasan Puscas, Felician Paul
  • Ferriol Galmés, Miquel
  • Rusek, Krzysztof
  • Geyer, Fabien
  • Cheng, Xiangle
  • Shi, Xiang
  • Xiao, Shihan
  • Scarselli, Franco
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
Graph neural networks (GNN) have shown outstanding applications in fields where data is essentially represented as graphs (e.g., chemistry, biology, recommendation systems). In this vein, communication networks comprise many fundamental components that are naturally represented in a graph-structured manner (e.g., topology, routing, signal interference). This position article presents GNNs as a fundamental tool for modeling, control and management of communication networks. GNNs represent a new generation of data-driven models that can accurately learn and reproduce the complex behaviors behind real-world networks. As a result, these models can be applied to a wide variety of networking use cases, such as planning, online optimization, or troubleshooting. The main advantage of GNNs over traditional neural networks lies in their unprecedented generalization capabilities when applied to other networks and configurations unseen during training. This is a critical feature for achieving practical data-driven solutions for networking. This article starts with a brief tutorial on GNNs and some potential applications to communication networks. Then, it presents two state-of-the-art GNN models respectively applied to wired and wireless networks. Lastly, it delves into the key open challenges and opportunities yet to be explored in this novel research area., 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 Artículo científico (JournalArticle)

Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case

  • Almasan Puscas, Felician Paul
  • Suárez-Varela Maciá, José Rafael
  • Rusek, Krzysztof
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Deep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve many relevant optimization problems (e.g., routing) in self-driving networks. However, existing DRL-based solutions applied to networking fail to generalize, which means that they are not able to operate properly when applied to network topologies not observed during training. This lack of generalization capability significantly hinders the deployment of DRL technologies in production networks. This is because state-of-the-art DRL-based networking solutions use standard neural networks (e.g., fully connected, convolutional), which are not suited to learn from information structured as graphs. In this paper, we integrate Graph Neural Networks (GNN) into DRL agents and we design a problem specific action space to enable generalization. GNNs are Deep Learning models inherently designed to generalize over graphs of different sizes and structures. This allows the proposed GNN-based DRL agent to learn and generalize over arbitrary network topologies. We test our DRL+GNN agent in a routing optimization use case in optical networks and evaluate it on 180 and 232 unseen synthetic and real-world network topologies respectively. The results show that the DRL+GNN agent is able to outperform state-of-the-art solutions in topologies never seen during training., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GB-C21), funded by MCIN/ AEI/10.13039/501- 100011033. 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. This work was also 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., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

TrackSign-labeled web tracking dataset

  • Castell Uroz, Ismael
  • Barlet Ros, Pere
Recent studies show that more than 95% of the websites available on the Internet contain at least one of the so-called web tracking systems. These systems are specialized in identifying their users by means of a plethora of different methods. Some of them (e.g., cookies) are very well known by most Internet users. However, the percentage of websites including more "obscure" and privacy-threatening systems, such as fingerprinting methods identifying a user's computer, is constantly increasing. Detecting those methods on today's Internet is very difficult, as almost any website modifies its content dynamically and minimizes its code in order to speed up loading times. This minimization and dynamicity render the website code unreadable by humans. Thus, the research community is constantly looking for new ways to discover unknown web tracking systems running under the hood. In this paper, we present a new dataset containing tracking information for more than 76 million URLs and 45 million online resources, extracted from 1.5 million popular websites. The tracking labeling process was done using a state-of-the-art discovery web tracking algorithm called TrackSign. The dataset also contains information about online security and the relation between the domains, the loaded URLs, and the online resource behind each URL. This information can be useful for different kinds of experiments, such as locating privacy-threatening resources, identifying security threats, or determining characteristics of the URL network graph., 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 (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

ePrivo.eu: An online service for automatic web tracking discovery

  • Castell Uroz, Ismael
  • Douha Prieto, Ismael
  • Basart Dotras, Meritxell
  • Mesegué Molina, Pol
  • Barlet Ros, Pere
Given the pervasiveness of web tracking practices on the Internet, many countries are developing and enforcing new privacy regulations to ensure the rights of their citizens. However, discovering websites that do not comply with those regulations is becoming very challenging, given the dynamic nature of the web or the use of obfuscation techniques. This work presents ePrivo, a new online service that can help Internet users, website owners, and regulators inspect how privacy-friendly a given website is. The system explores all the content of the website, including traffic from third parties and dynamically modified content. The ePrivo service combines different state-of-the-art tracking detection and classification methods, including TrackSign, to discover both previously known and zero-day tracking methods. After 6 months of service, ePrivo detected the largest browsing history trackers and more than 40k domains including cookies with a lifespan longer than one year, which is forbidden in some countries., This work was supported in part by the Spanish I+D+i Project TRAINER-A, funded by MCIN/AEI/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part by the Catalan Institution for Research and Advanced Studies (ICREA Academia)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

GAT-AD: Graph Attention Networks for contextual anomaly detection in network monitoring

  • Latif Martínez, Hamid
  • Suárez Varela, José
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
Network anomaly detection is essential to promptly detect and fix issues in the network. Particularly, detecting traffic anomalies enables the early detection of configuration errors, malicious activities, or equipment malfunctions that could lead to severe impact on the network. In this paper, we present GAT-AD, a Deep Learning-based anomaly detection solution for network monitoring systems, which integrates a custom neural network model based on Graph Attention Networks (GAT). Our solution monitors aggregated traffic on origin–destination flows and automatically defines contexts that group flows with similar past activity. The neural network model within GAT-AD can be efficiently trained in a self-supervised manner. We evaluate our solution against two state-of-the-art anomaly detection baselines also based on graph representations and Deep Learning, in two different datasets: (i) WaDi, which is a well-known dataset for anomaly detection in a distributed sensor network, and (ii) Abilene, where we inject synthetically-generated anomalies into a dataset with real-world traffic from a large-scale backbone network. The results show that GAT-AD outperforms the two anomaly detection baselines: in WaDi by 14.1% in recall and 10.07% in F1-score, and in the Abilene dataset by ˜ 17.5% recall with respect to the best baseline., 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), Spain. This work was also supported by the CHISTERA grant CHIST-ERA-22-SPiDDS-02 corresponding to the GRAPHS4SEC project (reference no PCI2023-145974-2) funded by the Agencia Estatal de Investigación, Spain through the PCI 2023 call. This work was also 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). This work was partially supported by the ORIGAMI project, funded by the Smart Networks and Services Joint Undertaking (SNS JU), Spain under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 101139270., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Demystifying content-blockers: Measuring their impact on performance and quality of experience

  • Castell Uroz, Ismael
  • Sánz García, Rubén
  • Solé Pareta, Josep
  • Barlet Ros, Pere
With the evolution of the online advertisement and tracking ecosystem, content-blockers have become the reference tool for improving the security, privacy and browsing experience when surfing the Internet. It is also commonly believed that using content-blockers to stop unsolicited content decreases the time needed for loading websites. In this work, we perform a large-scale study on the actual improvements of using content-blockers in terms of performance and quality of experience. For measuring it, we analyze the page size and loading times of the 100K most popular websites, as well as the most relevant QoE metrics, such as the Speed Index, Time to Interactive or the Cumulative Layout Shift, for the subset of the top 10K of them. Our experiments show that using content-blockers results in small improvements in terms of performance. However, contrary to popular belief, this has a negligible impact in terms of loading time and quality of experience. Moreover, in the case of small and lightweight websites, the overhead introduced by content-blockers can even result in decreased performance. Finally, we evaluate the improvement in terms of QoE based on the Mean Opinion Score (MOS) and find that two of the three studied content-blockers present an overall decrease between 3% and 5% instead of the expected improvement., 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 Artículo científico (JournalArticle)

Early detection of new web tracking methods across 1.5 million sites

  • Castell Uroz, Ismael
  • Sánchez de Mingo, Óscar
  • Barlet Ros, Pere
Current web tracking practices pose a constant threat to the privacy of Internet users. As a result, the research community has recently proposed different tools to combat well-known tracking methods. However, the early detection of new, previously unseen tracking systems is still an open research problem. In this paper, we present TrackSign+, a novel approach to discovering new web tracking methods. The main idea behind TrackSign+ is the use of code fingerprinting to identify common pieces of code shared across multiple domains. To detect tracking fingerprints, TrackSign+ builds a novel 4-mode network graph that captures the relationship between domains, URLs, online resources, and code fingerprints. We evaluated TrackSign+ with the 1.5M most popular Internet domains, including more than 45M web resources from almost 77M HTTP requests. Our results show that our method can detect new web tracking resources with high precision (over 92%). TrackSign+ was able to detect more than 300k new trackers, 800k new tracking resources, and 4.5M new tracking URLs, not yet detected by most popular pattern lists at the time. Finally, we also validated the effectiveness of TrackSign+ with more than 20 years of historical data from the Internet Archive., 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 Artículo científico (JournalArticle)

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

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

Building a Digital Twin for network optimization using graph neural networks

  • Ferriol Galmés, Miquel
  • Suárez-Varela Maciá, José Rafael
  • Paillissé Vilanova, Jordi
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Network modeling is a critical component of Quality of Service (QoS) optimization. Current networks implement Service Level Agreements (SLA) by careful configuration of both routing and queue scheduling policies. However, existing modeling techniques are not able to produce accurate estimates of relevant SLA metrics, such as delay or jitter, in networks with complex QoS-aware queueing policies (e.g., strict priority, Weighted Fair Queueing, Deficit Round Robin). Recently, Graph Neural Networks (GNNs) have become a powerful tool to model networks since they are specifically designed to work with graph-structured data. In this paper, we propose a GNN-based network model able to understand the complex relationship between the queueing policy (scheduling algorithm and queue sizes), the network topology, the routing configuration, and the input traffic matrix. We call our model TwinNet, a Digital Twin that can accurately estimate relevant SLA metrics for network optimization. TwinNet can generalize to its input parameters, operating successfully in topologies, routing, and queueing configurations never seen during training. We evaluate TwinNet over a wide variety of scenarios with synthetic traffic and validate it with real traffic traces. Our results show that TwinNet can provide accurate estimates of end-to-end path delays in 106 unseen real-world topologies, under different queuing configurations with a Mean Absolute Percentage Error (MAPE) of 3.8%, as well as a MAPE of 6.3% error when evaluated with a real testbed. We also showcase the potential of the proposed model for SLA-driven network optimization and what-if analysis., This publication is part of the Spanish I+D+i project TRAINER-A (ref.PID2020-118011GB-C21), funded by MCIN/ AEI/, Spain10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), Spain and the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia, Spain and the European Social Fund., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

A multidisciplinary model to quantify human uncertainty in human-centric cyber-physical-social systems: A 5G application use case

  • Alzate Mejía, Nestor
  • Perelló Muntan, Jordi
  • Santos Boada, Germán
  • Almeida Amazonas, José Roberto de
The emerging Human-Centric Networks (HCN) paradigm shifts the passive role of individuals to an active one, intertwining the uncertainty of network resource usage with human dynamics, which are difficult to analyze and predict. This phenomenon implies an increase in reciprocal interactions between Cyber-Physical-Social Systems (CPSS) and human activities, presenting the challenge of efficiently allocating network resources while taking into account qualitative human uncertainty. In this study, we propose a conceptual model that addresses and quantifies such uncertainties. The proposed model is characterized by its adaptability to various CPSS applications, facilitating its integration into existing applications and future innovations. The adaptability of the model is based on the application of the sociological concept of Boundary Objects (BO), which allows for the structuring of system components and the generation of a reference architecture that facilitates systematic problem solving. To evaluate the model, we propose a use case related to a Vehicle for Hire (VFH) application operating within a 5G network slice. The integration of the proposed model with the OMNET++ simulation framework has allowed to demonstrate the effectiveness of the model in intricate computational environments and have shown its capacity to incorporate previously overlooked elements that are essential for the optimal allocation of resources in CPSS. This study proposes a methodology for comprehending and mitigating the consequences of human uncertainty, emphasizing the significance of a multidisciplinary approach to resource allocation in sophisticated technological systems., This work was supported in part by the Spanish I+D+i Project TRAINER-A, funded by Ministerio de Ciencia, Innovación y Universidades (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part by the aid granted by the Sinfoni Project INV3164 of the Cooperative University of Colombia., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

ENERO: Efficient real-time WAN routing optimization with Deep Reinforcement Learning

  • Almasan Puscas, Felician Paul
  • Xiao, Shihan
  • Cheng, Xiangle
  • Shi, Xiang
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Wide Area Networks (WAN) are a key infrastructure in today’s society. During the last years, WANs have seen a considerable increase in network’s traffic and network applications, imposing new requirements on existing network technologies (e.g., low latency and high throughput). Consequently, Internet Service Providers (ISP) are under pressure to ensure the customer’s Quality of Service and fulfill Service Level Agreements. Network operators leverage Traffic Engineering (TE) techniques to efficiently manage the network’s resources. However, WAN’s traffic can drastically change during time and the connectivity can be affected due to external factors (e.g., link failures). Therefore, TE solutions must be able to adapt to dynamic scenarios in real-time. In this paper we propose Enero, an efficient real-time TE solution based on a two-stage optimization process. In the first one, Enero leverages Deep Reinforcement Learning (DRL) to optimize the routing configuration by generating a long-term TE strategy. To enable efficient operation over dynamic network scenarios (e.g., when link failures occur), we integrated a Graph Neural Network into the DRL agent. In the second stage, Enero uses a Local Search algorithm to improve DRL’s solution without adding computational overhead to the optimization process. The experimental results indicate that Enero is able to operate in real-world dynamic network topologies in 4.5 s on average for topologies up to 100 links., 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 (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Toward deep application-network integration: architectures, progress and opportunities

  • Serracanta Pujol, Berta
  • Gao, Kai
  • Ros Giralt, Jordi
  • Rodríguez Natal, Alberto
  • Contreras Murillo, Luis Miguel
  • Yang, Richard
  • Cabellos Aparicio, Alberto
With the rise of a new generation of applications (e.g., virtual and augmented reality, artificial intelligence, etc.) demanding stringent performance requirements, the need for networking solutions and architectures that can enable a higher quality of experience (QoE) has become increasingly important. While jointly optimizing application and network may increase the applications' QoE and simultaneously improve the utilization of network resources, such a paradigm has had limited success in real production networks. However, with the combination of revolutionary trends in computer processing demands, networking capabilities, and sustainable business models, it is high time the community explores the full potential of deeper integration between application and network. In this tutorial article, recent trends observed over the past few years are systematically reviewed. These include the paradigm shift in modern communication services toward computing-driven applications, such as on-site AI training, advances in programmable network technologies like software defined networking (SDN), and new business models incentivizing collaboration and cooperation between parties. Following this, successful scenarios that benefit from various forms of deeper network-application integration are reported, highlighting their considerable potential. A unified framework is then introduced, providing an overview of possible architecture paradigms for network-application integration and bringing awareness to existing abstractions, mechanisms, tools, and their potential combinations. The article concludes with a discussion of several remaining challenges in building practical network-application integrated systems., 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 Artículo científico (JournalArticle)

A one-pass clustering based sketch method for network monitoring

  • Fu, Yongquan
  • An, Lun
  • Shen, Siqi
  • Chen, Kai
  • Barlet Ros, Pere
Network monitoring solutions need to cope with increasing network traffic volumes, as a result, sketch-based monitoring methods have been extensively studied to trade accuracy for memory scalability and storage reduction. However, sketches are sensitive to skewness in network flow distributions due to hash collisions, and need complicated performance optimization to adapt to line-rate packet streams. We provide Jellyfish, an efficient sketch method that performs one-pass clustering over the network stream. One-pass clustering is realized by adapting the monitoring granularity from the whole network flow to fragments called subflows, which not only reduces the ingestion rate but also provides an efficient intermediate representation for the input to the sketch. Jellyfish provides the network-flow level query interface by reconstructing the network-flow level counters by merging subflow records from the same network flow. We provide probabilistic analysis of the expected accuracy of both existing sketch methods and Jellyfish. Real-world trace-driven experiments show that Jellyfish reduces the average estimation errors by up to six orders of magnitude for per-flow queries, by six orders of magnitude for entropy queries, and up to ten times for heavy-hitter queries., This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 61972409; in part by Hong Kong Research Grants Council (RGC) under Grant TRS T41-603/20-R, Grant GRF-16213621, and Grant ITF ACCESS; in part by the Spanish I+D+i project TRAINER-A, funded by MCIN/AEI/10.13039/501100011033, under Grant PID2020-118011GB-C21; and in part 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 Artículo científico (JournalArticle)

Evaluating a multidisciplinary model for managing human uncertainty in 5G cyber-physical-social systems

  • Alzate Mejía, Nestor
  • Perelló Muntan, Jordi
  • Santos Boada, Germán
  • Almeida Amazonas, José Roberto de
This paper presents a comprehensive evaluation of the previously introduced multidisciplinary model to quantify human uncertainty (MMtQHU) within a realistic 5G-enabled cyber–physical–social systems (CPSS) environment. The MMtQHU, which integrates human, social, and environmental factors into CPSS modeling, is applied to the Ingolstadt traffic scenario (InTAS), a detailed urban simulation reflecting high-traffic conditions. By modeling unpredictable driver behaviors, such as deviations from optimal routes, the study assesses the model’s effectiveness in managing human-induced uncertainties in vehicle-for-hire (VFH) applications. The evaluation shows that human uncertainty significantly impacts 5G network resource allocation and traffic dynamics. A comparative analysis of traditional resource allocation methods reveals their limitations in handling the dynamic nature of human behavior. These findings underscore the necessity for advanced, adaptive strategies, potentially leveraging artificial intelligence and machine learning to enhance the resilience and efficiency of 5G networks in CPSS environments. The study offers valuable insights for future advancements in robust and adaptive 5G infrastructure by highlighting the critical role of integrating human behavior into CPSS models., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GBC21) funded by MCIN/AEI/10.13039/501100011033 and by the aid granted by the Sinfoni project of the Cooperative University of Colombia., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

RouteNet-Fermi: network modeling with graph neural networks

  • Ferriol Galmés, Miquel
  • Paillissé Vilanova, Jordi
  • Suárez-Varela Maciá, José Rafael
  • Rusek, Krzysztof
  • Xiao, Shihan
  • Shi, Xiang
  • Cheng, Xiangle
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complexity, some models present limitations, such as the assumption of Markovian traffic in queuing theory models, or the high computational cost of network simulators. Recent advances in machine learning, such as Graph Neural Networks (GNN), are enabling a new generation of network models that are data-driven and can learn complex non-linear behaviors. In this paper, we present RouteNet-Fermi, a custom GNN model that shares the same goals as Queuing Theory, while being considerably more accurate in the presence of realistic traffic models. The proposed model predicts accurately the delay, jitter, and packet loss of a network. We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles — e.g., with complex non-Markovian models — and arbitrary routing and queue scheduling configurations. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators and scales accurately to larger networks. Our model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset of 1,000 samples, including network topologies one order of magnitude larger than those seen during training. Finally, we have also evaluated RouteNet-Fermi with measurements from a physical testbed and packet traces from a real-life network., This work was supported in part by the Spanish I+D+i Project TRAINER-A funded by the Ministry of Science and Innovation (MCIN)/State Investigation Agency (AEI)/10.13039/501100011033 under Grant PID2020-118011GB-C21, in part by the Catalan Institution for Research and Advanced Studies (ICREA), and in part by 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 Artículo científico (JournalArticle)

Verification of performance degradation in a telecommunications system due to the uncertainty of human users in the loop

  • Alzate Mejía, Nestor
  • Santos Boada, Germán
  • Almeida Amazonas, José Roberto de
The intensive use of new technologies that cause more interactions between systems and the daily activities of human users is changing the focus on how network re- sources should be managed. However, these changes can create challenges related to the level of uncertainty that people introduce to the system. In this context, this research study seeks to determine whether people’s uncertainty influences network performance and how significant its impact is. For these purposes, a simulated case study of a Vehicle for Hire application designed to run over a network slicing of a fifth-generation (5G) network. The simulations compared call drop rates in several settings configured to represent different levels of uncertainty, introducing random alterations to free channel planning reserved for the handover process. The simulation results reveal that the uncertainty specifically introduced by people exerts a high negative impact on network performance, evidencing the need to develop an algorithm that considers this uncertainty when managing resources within the 5G network core., This work has been supported by the Spanish Government through project TRAINER-A (PID2020-118011GB-C21) with FEDER contribution. Moreover, it has been supported by the Spanish Thematic Network under contract RED2018-102585-T (Go2Edge) and by the aid granted by the Sinfoni project INV2733 of the Cooperative University of Colombia., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

On the stability of the Kubernetes Horizontal Autoscaler control loop

  • Serracanta Pujol, Berta
  • Lukács, Andor
  • Rodríguez Natal, Alberto
  • Cabellos Aparicio, Alberto
  • Rétvári, Gábor
Kubernetes is a widely used platform for deploying and managing containerized applications due to its efficient elastic capabilities. The Horizontal Pod Autoscaler (HPA) in Kubernetes independently adjusts the number of pods for each service, yet these services often operate in an interconnected manner. This study aims to understand the effects of autoscaling events on a graph of interconnected services. To achieve this, we apply control theory to model the HPA’s behavior. We analyze the stability of this model, perform numerical simulations, and deploy a real testbed to evaluate the performance. Our findings demonstrate that the control theory-based model accurately predicts the HPA’s behavior, ensuring system stability with CPU utilization meeting desired thresholds and no traffic loss after a transitional period. The model provides insights into optimizing resource scheduling and improving application performance in Kubernetes environments. Additionally, we extend our model to the whole service graph to understand how individual scaling decisions influence the complex graphs of cloud applications., This work was supported in part by the Spanish I+D+i Project TowaRds fully AI-empowered NetwoRks, subproject A (TRAINER-A), funded by Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 under Grant PID2020-118011GB-C21; in part by the Catalan Institution for Research and Advanced Studies (ICREA) through the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia; in part by the European Social Fund; and in part by the National Research, Development and Innovation Fund of Hungary under Grant OTKA/ANN-135606, Grant OTKA/FK-135074, and Grant OTKA/FK-134604., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Network digital twin: context, enabling technologies, and opportunities

  • Almasan Puscas, Felician Paul
  • Ferriol Galmés, Miquel
  • Paillissé Vilanova, Jordi
  • Suárez-Varela Maciá, José Rafael
  • Perino, Diego
  • Lopez, Diego
  • Pastor Perales, Antonio Agustín
  • Harvey, Paul
  • Ciavaglia, Laurent
  • Wong, Leon
  • Xiao, Shihan
  • Ram, Vishnu
  • Shi, Xiang
  • Cheng, Xiangle
  • Cabellos Aparicio, Alberto
  • Barlet Ros, Pere
The proliferation of emergent network applications (e.g., telesurgery, metaverse) is increasing the difficulty of managing modern communication networks. These applications entail stringent network requirements (e.g., ultra-low deterministic latency), which hinders network operators to manage their resources efficiently. In this article, we introduce the network digital twin (NDT), a renovated concept of classical network modeling tools whose goal is to build accurate data-driven network models that can operate in real-time. We describe the general architecture of the NDT and argue that modern machine learning (ML) technologies enable building some of its core components. Then, we present a case study that leverages a ML-based NDT for network performance evaluation and apply it to routing optimization in a QoS-aware use case. Lastly, we describe some key open challenges and research opportunities yet to be explored to achieve effective deployment of NDTs in real-world networks., 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 Artículo científico (JournalArticle)

GraphCC: a practical graph learning-based approach to congestion control in datacenters

  • Bernárdez Gil, Guillermo
  • Suárez Varela, José
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Congestion Control (CC) plays a fundamental role in optimizing traffic in Datacenter Networks (DCNs). Currently, DCNs implement two main CC protocols: DCTCP and DCQCN. Both protocols are based on Explicit Congestion Notification (ECN), where switches mark packets when they detect congestion. Nowadays, network experts carefully set ECN parameters to optimize the average network performance. However, today’s DCNs experience rapid and abrupt changes that severely affect the network state (e.g., dynamic workloads, incasts), which leads to under-utilization and sub-optimal performance. In this paper we present GraphCC, a framework for in-network CC optimization. GraphCC relies on Multi-agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN), and is compatible with widely deployed ECN-based CC protocols. The proposed solution deploys distributed agents on switches that communicate with their neighbors to cooperate and optimize the global ECN configuration. In our evaluation, we test GraphCC with three real-world traffic workloads, focusing on its capability to accommodate scenarios unseen during training (e.g., traffic changes, failures). We compare GraphCC with a state-of-the-art MARL solution for ECN tuning, and observe that our method outperforms the state-of-the-art baseline in all evaluation scenarios, with improvements up to 20% in average Flow Completion Time, similar mean throughput (within 1%), and significant reductions in buffer occupancy (38.0-85.7%)., This publication is part of the Spanish I+D+i project TRAINER-A (reference PID2020-118011GB-C21), funded by MCIN/AEI/10.13039/ 501100011033, and the research has been partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia, and the European Social Fund. This work is also partially supported by the ORIGAMI project, funded by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 101139270, as well as by the CHISTERA grant CHIST-ERA-22-SPiDDS-02 corresponding to the GRAPHS4SEC project (reference PCI2023-145974-2), funded by the Agencia Estatal de Investigación through the PCI 2023 call., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

MAGNNETO: A graph neural network-based multi-agent system for traffic engineering

  • Bernárdez Gil, Guillermo
  • Suárez-Varela Maciá, José Rafael
  • López Brescó, Albert
  • Shi, Xiang
  • Xiao, Shihan
  • Cheng, Xiangle
  • Barlet Ros, Pere
  • Cabellos Aparicio, Alberto
Current trends in networking propose the use of Machine Learning (ML) for a wide variety of network optimization tasks. As such, many efforts have been made to produce ML-based solutions for Traffic Engineering (TE), which is a fundamental problem in Internet Service Provider (ISP) networks. Nowadays, state-of-the-art TE optimizers rely on traditional optimization techniques, such as Local search, Constraint Programming, or Linear programming. In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization. MAGNNETO deploys a set of agents across the network that learn and communicate in a distributed fashion via message exchanges between neighboring agents. Particularly, we apply this framework to optimize link weights in Open Shortest Path First (OSPF), with the goal of minimizing network congestion. In our evaluation, we compare MAGNNETO against several state-of-the-art TE optimizers in more than 75 topologies (up to 153 nodes and 354 links), including realistic traffic loads. Our experimental results show that, thanks to its distributed nature, MAGNNETO achieves comparable performance to state-of-the-art TE optimizers with significantly lower execution times. Moreover, our ML-based solution demonstrates a strong generalization capability to successfully operate in new networks unseen during training., This publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GBC21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), 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)