Conference Paper

Stable AQM Algorithm Based on AdaptiveWavelet Neural Network Controller

Dept. of Electr. & Electron. Eng., Yonsei Univ., Seoul
DOI: 10.1109/SICE.2006.314825 Conference: SICE-ICASE, 2006. International Joint Conference
Source: IEEE Xplore

ABSTRACT In this paper, we present the adaptive wavelet neural network (WNN) controller, which is trained by adaptive learning rates (ALRs), as an active queue management(AQM) in end-to-end TCP network. In TCP network, AQM is important to regulate the queue length and short round trip time by passing or dropping the packets at the intermediate routers. RED and PI algorithms have been used for AQM formerly. But these algorithms show weakness in the detection and control of the congestion under dynamically changing network situations. In our method, the WNN controller using ALRs is designed to overcome the problems, which adaptively controls the dropping probability of the TCP network and is trained by gradient-descent algorithm. We apply Lyapunov theorem to verify the stability of our proposed WNN controller. The simulation results show that the performance of WNN controller using ALRs is superior to that of PI controller

0 Bookmarks
 · 
45 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We consider a single link accessed by a single source which responds to congestion signals from the network. The design of controllers for such sources in the presence of feedback delay has received much attention recently. Here, we present conditions for the global, asymptotic stability and semiglobal exponential stability of congestion controllers. These conditions are natural extensions of conditions obtained through linearized analysis of such systems. Our result on exponential stability provides the missing link in the proof of how one obtains a single deterministic congestion control equation from a system with many congestion-controlled sources and random disturbances. Using numerical examples, we compare the conditions on the congestion-control parameters obtained using local and global stability analysis.
    IEEE Transactions on Automatic Control 07/2003; · 2.72 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Under the assumption that queueing delays will eventually become small relative to propagation delays, we derive stability results for a fluid flow model of end-to-end Internet congestion control. The theoretical results of the paper are intended to be decentralized and locally implemented: each end system needs knowledge only of its own round-trip delay. Criteria for local stability and rate of convergence are completely characterized for a single resource, single user system. Stability criteria are also described for networks where all users share the same round-trip delay. Numerical experiments investigate extensions to more general networks. Through simulations, we are able to evaluate the relative importance of queueing delays and propagation delays on network stability. Finally, we suggest how these results may be used to design network resources
    IEEE/ACM Transactions on Networking 01/2002; · 2.01 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a direct adaptive control method for stable path tracking of mobile robots using self recurrent wavelet neural network (SRWNN). As the proposed SRWNN is a modified model of the wavelet neural network (WNN), the SRWNN includes the basic ability of the WNN such as fast convergence. Besides the SRWNN has a property, unlike the WNN, that the SRWNN can store the past information of the network because a mother wavelet layer of the SRWNN is composed of self-feedback neurons. Accordingly, the SRWNN can easily cope with the unexpected change of the system. For the control problem, two SRWNNs are used as each direct adaptive controller for generating two control inputs, the translational and rotational displacement of the mobile robot. Specially, the gradient-descent method with adaptive learning rates (ALRs) is applied to train the parameters of the SRWNN controllers. The ALRs are derived from the discrete Lyapunov stability theorem out of consideration for the model of mobile robots, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.
    American Control Conference, 2005. Proceedings of the 2005; 07/2005