J. Mehnen et al. (Eds.): Applications of Soft Computing, AISC 58, pp. 115–123. springerlink.com © Springer-Verlag Berlin Heidelberg 2009 An Analysis of the Disturbance on TCP Network Congestion Mahdieh Shabanian, S. Hadi Hosseini, and Babak N. Araabi ∗ Abstract. In this study, the disturbance and uncertainty on nonlinear and time varying systems as Active Queue Management (AQM) is analyzed. Many of AQM schemes have been proposed to regulate a queue size close to a reference level with the least variance. We apply a normal range of disturbances and uncertainty such as variable user numbers, variable link capacity, noise, and unresponsive flows, to the three AQM methods: Random Early Detection (RED), Proportional-Integral (PI) and Improved Neural Network (INN) AQM. Then we examine some important factors for TCP network congestion control such as queue size, drop probability, variance and throughput in NS-2 simulator, and then compare three AQM algorithms with these factors on congestion conditions. We present the performance of the INN controller in desired queue tracking and disturbance rejection is high. 1 Introduction Congestion in Transmission Control Protocol (TCP) networks is the result of high needs for limited network resources. Moreover, when any high-speed links receive to one low-speed link, the congestion occurs. If the congestion continues, the undesired collapse phenomenon will occur. Active Queue Management (AQM) schemes are strategies which are implemented in routers to moderate TCP (Transmission Control Protocol) traffic. Random Early Detection (RED) is a popular method of an AQM scheme that presented by Floyd, and Jacobson in 1993 [2]. Although, this AQM is very simple and useful, however dynamics of the TCP networks are time-variant, and it is difficult to design RED parameters in order to obtain good performance under different congestion scenarios. In addition, it is difficult when we have any disturbance in TCP networks. Using the control theory, conventional controllers such as Proportional (P), Proportional-Integral (PI) [4], Proportional-Derivative (PD) [5], Proportional- Integral-Derivative (PID) [6], and adaptive controller such as Adaptive Random ∗Mahdieh Shabanian . S. Hadi Hosseini Science and Research branch, Islamic Azad University, Tehran, Iran e-mail: (m_shabanian, sh_hosseini)@itrc.ac.ir Babak N. Araabi School of Electrical and Computer Eng., University of Tehran, Tehran, Iran e-mail: araabi@ut.ac.ir