Sharif Digital Repository

A novel active queue management (AQM) method is proposed. This method, named NN-RED, is based on the use of a neural network for early congestion prediction. By simulations, it is demonstrated that the performance of the proposed approach is better than the random early detection (RED) method that is currently known as one of the best AQM methods in solving congestion problems. © The Institution of Engineering and Technology 2007  

Packet-level observations are representative of the high sensitivity of TCP/RED computer network behavior with respect to network/RED parameter variations. That is, while we do not have any control on network parameters, mis-choosing of the RED parameters results in complex non-periodic oscillations in the router queue length that may damage the Quality of Service requirements. Characterizing the nature of such behaviors, however, helps the network designers to modify the RED design method in order to achieve better overall performance. In this paper, we first investigate the effect of variations in different RED parameters on the network behavior and then seek for the origin of such complex... 

The growing interest in applications of Wireless Multimedia Sensor Networks (WMSNs) imposes new challenges on congestion control protocols in such networks. In this paper, we propose a new content-aware cross layer WMSN Congestion Control Protocol (WCCP) by considering the characteristics of multimedia content. WCCP employs a Source Congestion Avoidance Protocol (SCAP) in the source nodes, and a Receiver Congestion Control Protocol (RCCP) in the intermediate nodes. SCAP uses Group of Picture (GOP) size prediction to detect congestion in the network, and avoids congestion by adjusting the sending rate of source nodes and distribution of the departing packets from the source nodes. In... 

Although several analytical models have been proposed in the literature for different interconnection networks with different routing algorithms, there is only one work [M. Ould-Khaoua, An approximate performance model for partially adaptive routing algorithm in hypercubes, Microprocessors and Microsystems 23 (1999) 185-190] dealing with partially adaptive routing. It is not accurate enough especially in heavy traffic regions due to the rough approximation of assuming equal traffic rate over network channels. We show, however, such an approximation can greatly affect the accuracy of the model. This paper proposes an accurate analytical model to predict the average message latency in wormhole... 

In recent high speed networks such as ATM, dealing with different kinds of traffics have become a promising goal.Due to the dynamic nature and burstiness of aggregation of these various traffics, which is shown to be self similar, network congestion would occur more probably. Thus congestion control mechanisms (e.g. connection admission control) should be applied to preserve the quality of service of traffics passing through the network. In this paper we present a connection admission control (CAC) algorithm for self-similar traffics based on case based reasoning (CBR) which is almost a new concept in applied artificial intelligence. CBR is used to correct the estimation of the number of... 

The performance of a new robust AQM strategy for dynamically varying TCP/AQM networks is proposed. Network variations include in both network topology and traffic variations. The developed AQM is designed based on Coefficient Diagram Method (CDM), which is a new indirect pole placement method that considers the speed, stability and robustness of the closed loop system in terms of time domain specifications. Simulation results show different features of the proposed method. ©2005 IEEE  

Active Queue Management (AQM) policies provide an early indication of incipient congestion to the source. In this paper, we propose a new AQM policy that predicts the instantaneous queue length at the next time instant using adaptive filtering technique. To use this algorithm in fast routers, we have reduced its computational complexity. The proposed method uses a simple linear function as adaptive rule. We show that this adaptive congestion control method is able to control the oscillations in the instantaneous queue length. We compare the performance of our method with the other well-known AQM methods such as RED and PI which are also simulated by MATLAB. We also compare the computational... 

In this paper, a mathematical model and control theoretical framework for designing AQM controllers in networks supporting TCP Vegas is introduced. We have emphasized on a modified TCP Vegas algorithm that can respond to congestion signals through explicit congestion notification (ECN). The overall nonlinear delayed differential equations of the dynamics model of closed loop system have been derived based on TCP Vegas model. The model is then linearized to derive a transfer function representation between the packet marking probability and the bottleneck router queue length as the input and output of the modified TCP Vegas/AQM system. The model properties have been then examined especially... 

Beside the major objective of providing congestion control, achieving predictable queuing delay, maximizing link utilization, and robustness are the main objectives of an active queue management (AQM) controller. This paper proposes an improved queue dynamic model while incorporating the packet drop probability as well. By applying the improved model, a new compensated PID AQM controller is developed for Transmission Control Protocol/Internet Protocol (TCP/IP) networks. The non-minimum phase characteristic caused by Padé approximation of the network delay restricts the direct application of control methods because of the unstable internal dynamics. In this paper, a parameter-varying dynamic... 

When the network suffers from congestion, the core or edge routers signal the incidence of congestion through the active queue management (AQM) to the sources. The time-varying nature of the network dynamics and the complex process of retuning the current AQM algorithms for different operating points necessitate the development of a new AQM algorithm. Since the non-minimum phase characteristics of the network dynamics restrict direct application of the proportional-integral-derivative (PID) controller, we propose a compensated PID controller based on a new control strategy addressing the phase-lag and restrictions caused by the delay. Based on the unstable internal dynamics caused by the... 

AQM router aims primarily to control the network congestion through marking/dropping packets which are used as congestion feedback in traffic sources to balance their flow rate. However, stabilizing queuing delay and maximizing link utilization have been considered as the main control objectives, especially in media dominated networks. Usually, most of the AQM algorithms are designed for a nominal operating point. However, time-varying nature of network parameters frequently violates their robustness bounds. In this paper, a self-tuning compensated PID controller is proposed to address the time-varying nature of network conditions caused by parameter variations and unresponsive connections.... 

AQM router aims primarily to control the network congestion through marking/dropping packets which are used as congestion feedback in traffic sources to balance their flow rate. However, stabilizing queuing delay and maximizing link utilization have been considered as the main control objectives, especially in media dominated networks. Usually, most of the AQM algorithms are designed for a nominal operating point. However, time-varying nature of network parameters frequently violates their robustness bounds. In this paper, a self-tuning compensated PID controller is proposed to address the time-varying nature of network conditions caused by parameter variations and unresponsive connections.... 

Active queue management (AQM) mechanisms are designed to provide better support for end-to-end congestion control mechanisms of transmission control protocol (TCP) in TCP/IP networks. This paper introduces Direct Dynamic Matrix Control (D-DMC) as a new AQM method in dynamic TCP networks. Ability of the controller in handling system delay along with its simplicity and low computational loads makes D-DMC a privileged AQM method in high speed networks. The controller is designed based on a small signal linearized fluid-flow model of TCP/AQM networks. The computational complexity analysis as well as the MATLAB simulation results shows the out-performance of the developed controller for both... 

Due to the excellent properties of the model predictive controllers (MPC) in implementing on nonlinear and time varying systems, utilizing these controllers as Active Queue Management (AQM) strategy is proposed for congestion control of computer networks. However, high computational demand to solve the optimization problem exist in these controllers is a major obstacle when they are applied on fast large-scale constrained systems such as the computer networks. Small signal linearized model of the nonlinear TCP/AQM network is used to design MPC controller and then a neural network is trained to approximate the model predictive control strategy. Using this approach, due to the parallel... 

Utilizing model predictive controllers (MPC) as an active queue management scheme is investigated in this paper. Model based prediction of future output and determining optimized value of the control signal have made MPC as an advanced control strategy in various modern control systems. In this paper a new approach is proposed to alleviate the computational complexity of MPC in order to implement in fast dynamics systems like computer networks. Neural network approximation of MPC as an active queue management (AQM) method implemented here not only has less computational burden with respect to the common MPC approaches, but also results in better performance compare to the well-known AQM... 

A mobile ad hoc network is a collection of mobile hosts forming a temporary network on the fly, without using any fixed infrastructure. Characteristics of mobile ad hoc networks such as lack of central coordination, mobility of hosts, dynamically varying network topology, and limited availability of resources make QoS provisioning very challenging in such networks. In this paper, we introduce a fuzzy QoS traffic conditioner for mobile ad hoc networks. The proposed traffic conditioner consists of fuzzy admission control (FAC), fuzzy traffic rate controller (FTRC), and fuzzy scheduler (FS). The proposed FAC monitors the delay and available bandwidth and decides whether to accept or reject the...