Study on Feasibility of the FAIR Framework Based on Delay Statistics Analysis 


Vol. 46,  No. 2, pp. 293-301, Feb.  2021
10.7840/kics.2021.46.2.293


PDF
  Abstract

The class-based strict priority scheduling in Differentiated Services (DiffServ), which is adopted in the Internet, does not guarantee delay in a network with a topology where cycles exist. Asynchronous traffic shaping (ATS) technology, with the key theory that interleaved regulator (IR) does not increase the delay upper bound, was proposed as the solution to this problem. Based on the extension of the key theory of ATS, the flow aggregate-interleaved regulator (FAIR) framework is also proposed. It has been proven that FAIR framework is superior to the ATS in terms of complexity and delay bound. In this study, statistical performance characteristics of the ATS and FAIR frameworks are analyzed with simulations and compared with a FIFO scheduling framework without regulators. In the simulation without cycle, statistical delay performance was in the order of FIFO, FAIR, and ATS. In the simulation with cycle, statistical delay performance was in the order of FAIR, FIFO, and ATS. This proved that the FAIR framework is superior to the ATS in terms of both delay bound and average delay.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Kwon and J. Joung, "Study on Feasibility of the FAIR Framework Based on Delay Statistics Analysis," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 293-301, 2021. DOI: 10.7840/kics.2021.46.2.293.

[ACM Style]

Juhyeok Kwon and Jinoo Joung. 2021. Study on Feasibility of the FAIR Framework Based on Delay Statistics Analysis. The Journal of Korean Institute of Communications and Information Sciences, 46, 2, (2021), 293-301. DOI: 10.7840/kics.2021.46.2.293.

[KICS Style]

Juhyeok Kwon and Jinoo Joung, "Study on Feasibility of the FAIR Framework Based on Delay Statistics Analysis," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 293-301, 2. 2021. (https://doi.org/10.7840/kics.2021.46.2.293)