4th International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities

Research Article

Relative Rate Reduction Based Control with Adjustable Congestion Level

Download481 downloads
  • @INPROCEEDINGS{10.4108/tridentcom.2008.3040,
        author={P\^{e}ter H\^{a}ga and Ferenc  T\^{o}th and Istv\^{a}n Csabai and G\^{a}bor Vattay},
        title={Relative Rate Reduction Based Control with Adjustable Congestion Level},
        proceedings={4th International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks \& Communities},
        publisher={ICST},
        proceedings_a={TRIDENTCOM},
        year={2010},
        month={5},
        keywords={congestion control transport protocol TCP},
        doi={10.4108/tridentcom.2008.3040}
    }
    
  • Péter Hága
    Ferenc Tóth
    István Csabai
    Gábor Vattay
    Year: 2010
    Relative Rate Reduction Based Control with Adjustable Congestion Level
    TRIDENTCOM
    ICST
    DOI: 10.4108/tridentcom.2008.3040
Péter Hága1,*, Ferenc Tóth1,*, István Csabai2,*, Gábor Vattay2,*
  • 1: Eötvös University, Budapest
  • 2: Collegium Budapest – Institute for Advanced Study
*Contact email: haga@elte.hu, feri@elte.hu, csabai@colbud.hu, vattay@colbud.hu

Abstract

In Future Internet it is possible to change elements of congestion control in order to eliminate jitter and batch loss caused by the current control mechanisms based on packet loss events. We investigate the fundamental problem of adjusting sending rates to achieve optimal utilization of highly variable bandwidth of a network path using accurate packet rate information. This is done by continuously controlling the sending rate with a function of the measured packet rate at the receiver. We propose the relative loss of packet rate between the sender and the receiver (Relative Rate Reduction, RRR) as a new accurate and continuous measure of congestion of a network path, replacing the erratically fluctuating packet loss. We demonstrate that with choosing various RRR based feedback functions the optimum is reached with adjustable congestion level. The proposed method guarantees fair bandwidth sharing of competitive flows. Finally we present testbed experiments to demonstrate the performance of the algorithm.