Signal Processing and Information Technology. First International Joint Conference, SPIT 2011 and IPC 2011, Amsterdam, The Netherlands, December 1-2, 2011, Revised Selected Papers

Research Article

Fuzzy Three Time Scale Congestion Controller

Download
424 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-32573-1_6,
        author={Mehdi Mohtashamzadeh and Mohsen Soryani},
        title={Fuzzy Three Time Scale Congestion Controller},
        proceedings={Signal Processing and Information Technology. First International Joint Conference, SPIT 2011 and IPC 2011, Amsterdam, The Netherlands, December 1-2, 2011, Revised Selected Papers},
        proceedings_a={SPIT \& IPC},
        year={2012},
        month={10},
        keywords={Self similarity multi time scale long range dependency fuzzy congestion control},
        doi={10.1007/978-3-642-32573-1_6}
    }
    
  • Mehdi Mohtashamzadeh
    Mohsen Soryani
    Year: 2012
    Fuzzy Three Time Scale Congestion Controller
    SPIT & IPC
    Springer
    DOI: 10.1007/978-3-642-32573-1_6
Mehdi Mohtashamzadeh1,*, Mohsen Soryani1,*
  • 1: Iran University of Science & Technology
*Contact email: Mohtashamzadeh@gmail.com, soryani@iust.ac.ir

Abstract

Although loss rate, length of the queues in the routers and throughput are affected by self similar property of traffic, but classic congestion control algorithms work in short time scales and do not consider self similarity and long range (time) dependency phenomenon of data. To profit these properties, researchers have proposed several methods. Multi time scale congestion control is one of the successful ways to adapt with self similar traffic and predict network status. In this research, a three part structure has been implemented in which second and third parts take advantage of fuzzy engines. Results show throughput improvement in case of using fuzzy three time scale controller instead of a two time scale controller or a classic controller such as New Reno.