Now showing items 21-40 of 49

    • FaRNet: fast recognition of high multi-dimensional network traffic patterns 

      Paredes Oliva, Ignasi; Barlet Ros, Pere; Dimitropoulos, Xenofontas (ACM, 2013)
      Conference lecture
      Restricted access - publisher's policy
      Extracting knowledge from big network traffic data is a matter of foremost importance for multiple purposes ranging from trend analysis or network troubleshooting to capacity planning or traffic classification. An extremely ...
    • Feature engineering for deep reinforcement learning based routing 

      Suárez-Varela Maciá, José Rafael; Mestres Sugrañes, Albert; Yu, Junlin; Kuang, Li; Feng, Haoyu; Barlet Ros, Pere; Cabellos Aparicio, Alberto (Institute of Electrical and Electronics Engineers (IEEE), 2019)
      Conference report
      Open Access
      Recent advances in Deep Reinforcement Learning (DRL) techniques are providing a dramatic improvement in decision-making and automated control problems. As a result, we are witnessing a growing number of research works that ...
    • Flow monitoring in software-defined networks: finding the accuracy/performance tradeoffs 

      Suárez Varela, José; Barlet Ros, Pere (2018-04-22)
      Article
      Open Access
      In OpenFlow-based Software-Defined Networks, obtaining flow-level measurements, similar to those provided by NetFlow/IPFIX, is challenging as it requires to install an entry per flow in the flow tables. This approach does ...
    • Identifying the root cause of video streaming issues in mobile devices 

      Dimopoulos, Georgios; Leontiadis, Ilias; Barlet Ros, Pere; Papagiannaki, Konstantina; Steenkiste, Peter (Association for Computing Machinery (ACM), 2015)
      Conference report
      Restricted access - publisher's policy
      Video streaming on mobile devices is prone to a multi-tude of faults and although well established video Qual-ity of Experience (QoE) metrics such as stall frequencyare a good indicator of the problems perceived by theuser, ...
    • Independent comparison of popular DPI tools for traffic classification 

      Bujlow, Tomasz; Carela Español, Valentín; Barlet Ros, Pere (2015-01-15)
      Article
      Open Access
      Deep Packet Inspection (DPI) is the state-of-the-art technology for traffic classification. According to the conventional wisdom, DPI is the most accurate classification technique. Consequently, most popular products, ...
    • Is our ground-truth for traffic classification reliable? 

      Carela Español, Valentín; Bujlow, Tomasz; Barlet Ros, Pere (2014)
      Conference report
      Restricted access - publisher's policy
      The validation of the different proposals in the traffic classification literature is a controversial issue. Usually, these works base their results on a ground-truth built from private datasets and labeled by techniques ...
    • ITMgen - A first-principles approach to generating synthetic interdomain traffic matrices 

      Mikians, Jakub; Laoutaris, Nikolaos; Dhamdhere, Amogh; Barlet Ros, Pere (Institute of Electrical and Electronics Engineers (IEEE), 2013)
      Conference report
      Open Access
      We present the design and evaluation of ITMgen, a tool for generating synthetic but representative Interdomain Traffic Matrices (ITMs). ITMgen is motivated by the observation that gravity-based models do not reflect ...
    • Knowledge-defined networking 

      Mestres Sugrañes, Albert; Rodríguez Natal, Alberto; Carner Marsal, Josep; Barlet Ros, Pere; Alarcón Cot, Eduardo José; Sole, Marc; Muntés Mulero, Victor; Meyer, David; Barkai, Sharon; Hibbett, Mike J.; Estrada, Giovani; Coras, Florin-Tudorel; Ermagan, Vina; Latapie, Hugo; Cassar, Chris; Evans, John; Walrand, Jean; Cabellos Aparicio, Alberto (2017-07-01)
      Article
      Open Access
      The research community has considered in the past the application of Artificial Intelligence (AI) techniques to control and operate networks. A notable example is the Knowledge Plane proposed by D.Clark et al. However, ...
    • Load shedding in network monitoring applications 

      Barlet Ros, Pere (Universitat Politècnica de Catalunya, 2008-12-15)
      Doctoral thesis
      Open Access
      Monitoring and mining real-time network data streams are crucial operations for managing and operating data networks. The information that network operators desire to extract from the network traffic is of different size, ...
    • Measuring video QoE from encrypted traffic 

      Dimopoulos, Georgios; Leontiadis, Ilias; Barlet Ros, Pere; Papagiannaki, Konstantina (Association for Computing Machinery (ACM), 2016)
      Conference report
      Restricted access - publisher's policy
      Tracking and maintaining satisfactory QoE for video streaming services is becoming a greater challenge for mobile network operators than ever before. Downloading and watching video content on mobile devices is currently a ...
    • Network measurements for web tracking analysis and detection: A tutorial 

      Castell Uroz, Ismael; Solé Pareta, Josep; Barlet Ros, Pere (2020-12)
      Article
      Open Access
      Digital society has developed to a point where it is nearly impossible for a user to know what it is happening in the background when using the Internet. To understand it, it is necessary to perform network measurements ...
    • Network Polygraph: An innovative network visibility service (not only) for NRENs 

      Barlet Ros, Pere; Sanjuàs Cuxart, Josep; Solé Pareta, Josep; Gandía, Maria Isabel; Malagón, Chelo (2015)
      Conference lecture
      Open Access
      We present Network Polygraph (https://polygraph.io), a network monitoring service based on NetFlow/IPFIX that benefits from more than 10 years of research in the fields of network monitoring and traffic classification at ...
    • Performance of direct-oversampling correlator-type receivers in chaos-based DS-CDMA systems over frequency non-selective fading channels 

      Nguyen, Xuan Quyen; Barlet Ros, Pere (2017-03-08)
      Article
      Open Access
      In this paper, we present a study on the performance of direct-oversampling correlator-type receivers in chaos-based direct-sequence code division multiple access systems over frequency non-selective fading channels. At ...
    • (Position paper) Characterizing the behavior of small producers in smart grids: A data sanity analysis 

      Stefan, Maria; Gutiérrez López, José Manuel; Barlet Ros, Pere; Prieto Araujo, Eduardo; Gomis Bellmunt, Oriol; Olsen, Rasmus L. (Elsevier, 2020)
      Article
      Open Access
      Renewable energy production throughout low-voltage grids has gradually increased in electrical distribution systems, therefore introducing small energy producers - prosumers. This paradigm challenges the traditional ...
    • RouteNet: leveraging graph neural networks for network modeling and optimization in SDN 

      Rusek, Krzysztof; Suárez-Varela Maciá, José Rafael; Almasan Puscas, Felician Paul; Barlet Ros, Pere; Cabellos Aparicio, Alberto (2020-06-05)
      Article
      Open Access
      Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to produce accurate predictions of Key ...
    • Routing based on deep reinforcement learning in optical transport networks 

      Suárez-Varela Maciá, José Rafael; Mestres Sugrañes, Albert; Yu, Junlin; Kuang, Li; Feng, Haoyu; Barlet Ros, Pere; Cabellos Aparicio, Alberto (2019)
      Conference report
      Restricted access - publisher's policy
      This paper addresses the use of Deep Reinforcement Learning for automatic routing in Optical Transport Networks at the electrical-layer level. We propose a DRL-based solution that achieves both high performance and fast learning.
    • Routing in optical transport networks with deep reinforcement learning 

      Suárez Varela, José; Mestres Sugranyes, Albert; Yu, Junlin; Kuang, Li; Feng, Haoyu; Cabellos Aparicio, Alberto; Barlet Ros, Pere (Institute of Electrical and Electronics Engineers (IEEE), 2019)
      Article
      Open Access
      Deep reinforcement learning (DRL) has recently revolutionized the resolution of decision-making and automated control problems. In the context of networking, there is a growing trend in the research community to apply DRL ...
    • SBAR: SDN flow-based monitoring and application recognition 

      Suárez-Varela Maciá, José Rafael; Barlet Ros, Pere (Association for Computing Machinery (ACM), 2018)
      Conference report
      Restricted access - publisher's policy
      We present SBAR, a monitoring system compliant with OpenFlow that provides flow-level measurement reports similar to those of NetFlow in traditional networks, but additionally enriched with labels that classify flows at ...
    • Scan detection under sampling: a new perspective 

      Paredes Oliva, Ignasi; Barlet Ros, Pere; Solé Pareta, Josep (2013-04-01)
      Article
      Restricted access - publisher's policy
      In tests using the same fraction of packets for comparison, packet sampling outperformed flow sampling for scan detection, while both selective sampling and a proposed extension that uses significantly less resources were ...
    • Skettching the delay: tracking temporally uncorrelated flow-level latancies 

      Sanjuàs Cuxart, Josep; Barlet Ros, Pere; Duffield, Nick; Kompella, Ramana (2011)
      Conference report
      Restricted access - publisher's policy
      Packet delay is a crucial performance metric for real-time, network-based applications. Obtaining per-flow delay measurements is particularly important to network operators, but is computationally challenging in high-speed ...