Artículos de revista DAC - AKS Aldizkari artikuluak

Permanent URI for this collection

http://hdl.handle.net/2454/10465

Browse

Browsing Artículos de revista DAC - AKS Aldizkari artikuluak by Author "Aracil Rico, Javier"

Now showing 1 - 5 of 5
  • Thumbnail Image
    PublicationOpen Access
    Analysis and stochastic characterization of TCP flows
    (Springer, 2000) Aracil Rico, Javier; Morató Osés, Daniel; Izal Azcárate, Mikel; Automática y Computación; Automatika eta Konputazioa
    Since the most Internet services use TCP as a transport protocol there is a growing interest in the characterization of TCP flows. However, the flow characteristics depend on a large number of factors, due to the complexity of the TCP. As a result, the TCS characteristics are normally studies by means of simulations or controlled network setups. In this paper we propose a TCP characterization based on a generic model based of stochastic flow with burstiness and throughput (((σ, ρ)-constraints), which is useful in order to characterize flows in ATM and other flow-switched networks. The model is obtained through extensive analysis of a real traffic trace, comprising an approximate number of 1,500 hosts and 1,700,000 TCP connections. The results suggests that TCP connections in the wide area Internet have low throughput while the packet bursts do not suffer an exponential increase, as indicated by the slow-start behavior. On the other hand, the impact of the connection establishment phase is striking. We note that the throughput of the TCP flow is approximately half the throughput which is obtained in the data transfer phase, namely after the connection has been established.
  • Thumbnail Image
    PublicationOpen Access
    Delay-throughput curves for timer-based OBS burstifiers with light load
    (IEEE, 2006) Izal Azcárate, Mikel; Aracil Rico, Javier; Morató Osés, Daniel; Magaña Lizarrondo, Eduardo; Automática y Computación; Automatika eta Konputazioa
    The OBS burstifier delay-throughput curves are analyzed in this paper. The burstifier incorporates a timer-based scheme with minimum burst size, i. e., bursts are subject to padding in light-load scenarios. Precisely, due to this padding effect, the burstifier normalized throughput may not be equal to unity. Conversely, in a high-load scenario, padding will seldom occur. For the interesting light-load scenario, the throughput delay curves are derived and the obtained results are assessed against those obtained by trace-driven simulation. The influence of long-range dependence and instantaneous variability is analyzed to conclude that there is a threshold timeout value that makes the throughput curves flatten out to unity. This result motivates the introduction of adaptive burstification algorithms, that provide a timeout value that minimizes delay, yet keeping the throughput very close to unity. The dependence of such optimum timeout value with traffic long-range dependence and instantaneous burstiness is discussed. Finally, three different adaptive timeout algorithms are proposed, that tradeoff complexity versus accuracy.
  • Thumbnail Image
    PublicationOpen Access
    Internet traffic shaping for IP over WDM links with source output buffering or multiple parallel wavelengths
    (Kluwer Academic Publishers, 2001) Aracil Rico, Javier; Izal Azcárate, Mikel; Morató Osés, Daniel; Automática y Computación; Automatika eta Konputazioa
    Since the number of wavelengths per fiber is growing in an exponential fashion the over- flow traffic can be routed through overflow lightpaths, thus providing an ideal network with near-infinite capacity and almost no-buffering. Such unprecedented bandwidth growth in the network backbone is only limited by the processing speed of the electronic elements. Even though multiple parallel high-speed channels (lightpaths) are provided between IP routers the switching speed of the latter is an order of magnitude below the lightpath transmission speed. As a result, minimizing transfer delay is not only a matter of forwarding traffic as fast as possible but to shape traffic so that the input queues of the destination routers do not over-flow. Even though it is desirable to exploit the WDM capabilities to forward traffic in parallel channels in order to nearly eliminate the router output buffering, it turns out that the extreme burstiness of Internet traffic is even increased by routing part of the traffic through a backup channel. Instead, the use of source output buffering for traffic shaping purposes proves more beneficial. In this paper, we examine the typical scenario of a static WDM network with several wavelengths between IP routers. In a simple configuration of a primary and over flow lightpath the results show that if 3% of the traffic is routed through the over flow lightpath then the packet forwarding speed in the destination router should be increased in 20% in order to obtain the same transfer delay as with the single lightpath configuration with source output buffering.
  • Thumbnail Image
    PublicationOpen Access
    On capacity planning for the GMPLS network control plane
    (Springer US, 2008) Morató Osés, Daniel; Aracil Rico, Javier; Fernández Palacios, Juan P.; González de Dios, Óscar; Lobo Poyo, Jesús F.; Automática y Computación; Automatika eta Konputazioa
    This paper presents capacity planning rules for the control plane of all-optical networks featuring GMPLS and RSVP-TE as a connection setup protocol. As per RSVP standard, a refresh message mechanism is incorporated to RSVP such that the state is periodically refreshed on a link per link basis. We provide analytical expressions for the bandwidth and buffer sizes to be provided such that no flows are torn down due to lack of refresh messages. Our findings show that small buffers (several KBytes) suffice to sustain the signaling load for as much as 400 RSVP flows per link, with the simplest RSVP refresh mechanism (neither using link bundling nor acknowledgments). On the other hand, we also find the packet drop probability per link for a given network topology for the case that the flow survival probability is larger than a given threshold. We provide numerical examples based on the COST 239 european network topology and real RSVP traffic traces from early-commercial switching equipment.
  • Thumbnail Image
    PublicationOpen Access
    Online detection of pathological TCP flows with retransmissions in high-speed networks
    (Elsevier, 2018) Miravalls-Sierra, Eduardo; Muelas, David; Ramos, Javier; López de Vergara, Jorge E.; Morató Osés, Daniel; Aracil Rico, Javier; Automática y Computación; Automatika eta Konputazioa
    Online Quality of Service (QoS) assessment in high speed networks is one of the key concerns for service providers, namely to detect QoS degradation on-the-fly as soon as possible and avoid customers’ complaints. In this regard, a Key Performance Indicator (KPI) is the number of TCP retransmissions per flow, which is related to packet losses or increased network and/or client/server latency. However, to accurately detect TCP retransmissions the whole sequence number list should be tracked which is a challenging task in multi-Gb/s networks. In this paper we show that the simplest approach of counting as a retransmission a packet whose sequence number is smaller than the previous one is enough to detect pathological flows with severe retransmissions. Such a lightweight approach eliminates the need of tracking the whole TCP flow history, which severely restricts traffic analysis throughput. Our findings show that low False Positive Rates (FPR) and False Negative Rates (FNR) can be achieved in the detection of such pathological flows with severe retransmissions, which are of paramount importance for QoS monitoring. Most importantly, we show that live detection of such pathological flows at 10 Gb/s rate per processing core is feasible.