Conference Paper

Synchronization of TCP Flows in Networks with Small DropTail Buffers

Electrical and Computer Engineering Department, University of Massachusetts, Amherst, MA 01003, USA.
DOI: 10.1109/CDC.2005.1583249 Conference: Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC '05. 44th IEEE Conference on
Source: IEEE Xplore


A recent fluid-model formulation of an Internet congestion-control problem considers routers with small Droptail buffers. This paper is interested in the oscillatory regime of such networks and considers a topology where two TCP-controlled flows (each regulated by separate (edge) routers) merge to compete for bandwidth at a common (core) router. We describe this dynamic using a weakly-coupled oscillator model and analyze the coherence of oscillation as a function of coupling strength. We show that increased coupling leads to increased coherence and to larger variations in the arrival flow at the core router. The coupling strength can be expressed in terms of network parameters.

Download full-text


Available from: C.V. Hollot, Aug 14, 2014
22 Reads
  • Source
    • "There are several queue management strategies adopted by routers. Currently, the DropTail [21] scheme is widely used in the routers. With this strategy, when the buffers are full, all incoming traffic has to be dropped. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This article studies the transmission control protocol (TCP) synchronization effect in optical burst switched networks. Synchronization of TCP flows appears when optical bursts with segments from different flows inside are dropped in the network causing flow congestion windows decreasing simultaneously. In this article, this imminent effect is studied with different assembly schemes and network scenarios. Different metrics are applied to quantitatively assess synchronization with classical assembly schemes. A new burst assembly scheme is proposed that statically or dynamically allocates flows to multiple assembly queues to control flow aggregation within the assembly cycle. The effectiveness of the scheme has been evaluated, showing a good improvement in optical link utilization.
    Photonic Network Communication 12/2009; 18(3):323-333. DOI:10.1007/s11107-009-0195-9 · 0.79 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a novel, dynamical systems-based approach for analysis and control of the complex dynamic behavior arising in communication networks. Specifically, we consider the active queue management (AQM) problem and study the non-equilibrium behavior observed as a result of the interaction between deterministic queueing and nonlinear flow-control dynamics using a stochastic characterization. The asymptotic dynamics are interpreted using invariant measures of certain stochastic operators. For computational tractability, we use set-oriented numerical methods to construct finite-dimensional Markov models including control Markov chains and hidden Markov models. Based on the stochastic model constructed, we pose and solve the AQM control problem using Markov decision processes (MDPs). The framework developed is demonstrated through a numerical study of an example AQM scheme, which shows persistent non-equilibrium queue behavior under the optimal control strategy
    Decision and Control, 2006 45th IEEE Conference on; 01/2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this note we analyse various stability properties of the max-min fair Rate Control Protocol (RCP) operating with small buffers. We first tackle the issue of stability for networks with arbitrary topologies. We prove that the max-min fair RCP fluid model is globally stable in the absence of propagation delays, and also derive a set of conditions for local stability when arbitrary heterogeneous propagation delays are present. The network delay stability result assumes that, at equilibrium, there is only one bottleneck link along each route. Lastly, in the simpler setting of a single link, single delay model, we investigate the impact of the loss of local stability via a Hopf bifurcation.
    IEEE Transactions on Automatic Control 12/2007; 54(8). DOI:10.1109/TAC.2009.2022115 · 2.78 Impact Factor
Show more