			Home About us Contact

Congestion Control Mechanism (congestion + control_mechanism)

Distribution by Scientific Domains

Engineering	75%

Selected Abstracts

Steady state and transient state behaviours analyses of TCP connections considering interactions between TCP connections and network

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, Issue 7 2005
Hiroyuki Hisamatsu
Abstract The Internet uses a window-based congestion control mechanism in transmission control protocol (TCP). In the literature, there have been a great number of analytical studies on TCP. Most of those studies have focused on the statistical behaviour of TCP by assuming a constant packet loss probability in the network. However, the packet loss probability, in reality, changes according to the packet transmission rates from TCP connections. Conversely, the window size of a TCP connection is dependent on the packet loss probability in the network. In this paper, we explicitly model the interaction between the congestion control mechanism of TCP and the network as a feedback system. By using this model, we analyse the steady state and the transient state behaviours of TCP. We derive the throughput and the packet loss probability of TCP, and the number of packets queued in the bottleneck router. We then analyse the transient state behaviour using a control theoretic approach, showing the influence of the number of TCP connections and the propagation delay on the transient state behaviour of TCP. Copyright © 2005 John Wiley & Sons, Ltd. [source]

An Internet friendly transport protocol for continuous media over best effort networks

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, Issue 10 2002
Hala ElAarag
Abstract In this paper, we design and evaluate an Internet friendly transport-level protocol (IFTP) for solving the TCP-friendly problem. IFTP has two modes of operation. In the standard mode, the IFTP connection faithfully emulates the behaviour of TCP in order to roughly obtain a bandwidth equal to that of a TCP connection. In the extended mode, a simple modification is used to grant QoS-differentiated services to selected connections. Connections running in the extended mode can get enhanced bandwidth while still emulating the general behaviour of TCP. We develop an analytical model for the congestion control mechanism of IFTP. We also derive analytically the amount of bandwidth that IFTP may be able to claim from TCP in ideal and non-ideal environments. We evaluate IFTP through simulation and prove its TCP friendliness as well as provide performance results on some of the important metrics such as packet delay, delay jitter, packet loss and link utilization. Copyright © 2002 John Wiley & Sons, Ltd. [source]

Cross-layer design to improve elastic traffic performance in WLANs

INTERNATIONAL JOURNAL OF NETWORK MANAGEMENT, Issue 3 2008
Stephane Lohier
In this paper, we are interested in improving TCP flow performance when a short loss of 802.11 signal leads to losing segments and triggers inappropriately TCP congestion control mechanisms. A set of measurements in a common wireless environment with signal losses due to mobility or interference is made to highlight the distinct MAC and TCP loss recovery levels and the lack of interactions between them. Initially, we demonstrate the interest of adapting the 802.11 MAC layer Retry Limit parameter in the case of signal losses due to distance or obstacles (mobility). Thus, a first-level loss differentiation algorithm (LDA) acting at the MAC layer is proposed to improve TCP flow performance in the case of segment losses due to mobility. Hence, for a signal failure, the MAC layer reacts consequently by dynamically adapting the Retry Limit parameter. This adaptation allows avoiding a costly end-to-end TCP loss recovery. Segment losses due to interference are differentiated from those due to congestion through the use of a second-level LDA. The latter is a cross-layer LDA acting at the TCP layer but using a specific 802.11 parameter, the AckFailureCount, to realize the targeted loss differentiation. The TCP NewReno version is then adapted in order to integrate the cross-layer LDA results and to avoid reducing the TCP congestion window unsuitably. The efficiency and completeness of a solution integrating both LDA schemes is then discussed. Copyright © 2007 John Wiley & Sons, Ltd. [source]

A reliable cooperative and distributed management for wireless industrial monitoring and control

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, Issue 2 2010
Dr S. Manfredi
Abstract This paper is concerned with the analysis, design and validation of a reliable management strategy for industrial monitoring and control over wireless sensor network (WSN). First, we investigate the interactions between contention resolution and congestion control mechanisms in Wireless Industrial Sensor Network (briefly WISN). An extensive set of simulations are performed in order to quantify the impacts of several network parameters (i.e. buffer, sensors reporting rate) on the overall network performance (i.e. reliability, packet losses). This calls for cross-layer mechanisms for efficient data delivery over WISN. Second, a reliable sink resource allocation strategy based on log-utility fairness criteria is proposed. It is shown that the resource sink manager can plan strategies to better allocate the available resource among competing sensors. Finally, the analysis, design and validation of a reliable sinks cooperative control for WISN are introduced. A sufficient condition for wireless network stability in presence of multiple sinks and heterogeneous sensors with different time delays is given and it is used for network parameters design. The stability condition and the resulting cooperative control performance in terms of fairness, link utilization, packet losses, reliability and latency are validated by Matlab/Simulink-based simulator TrueTime, which facilitates co-simulation of controller task execution in real-time kernels and in the wireless network environment. Copyright © 2009 John Wiley & Sons, Ltd. [source]