*Generation of self similar network traffic using DFGN algorithm / Che Ku Noreymie Che Ku Jusoh.*Degree thesis, Universiti Teknologi MARA.

## Abstract

This thesis discusses the generation of network traffic using discrete Fractional

Gaussian Noise (dFGN) algorithm. Since the traffic on a number of existing networks is

bursty, much research focuses on how to capture the characteristics of traffic to reduce

the impact of burstiness. Conventional traffic models do not represent the characteristics

of burstiness well, but self–similar traffic models provide a closer approximation. Selfsimilar traffic models have two fundamental properties, long–range dependence and

infinite variance, which have been found in a large number of measurement of real

traffic. Self-similar traffic models also have been found to be more appropriate for the

representation of bursty telecommunication traffic.

The main starting point for self-similar traffic generation is the production of

fractional Brownian motion (FBM) or fractional Gaussian noise (FGN). Fractional

Brownian motion or Fractional Gaussian Noise is not only of interest for generation of

network traffic. Its properties have been investigated by researchers in theoretical

physics, probability, statistics, hydrology, biology, and many others. As a result, the

techniques that have been used to study this Gaussian process are quite diverse, and it

may take some effort to study them. Undoubtedly, this also makes the field more

interesting.

After generating FBM sample traces, a further transformation needs to be

conducted with testing the result to produce the self-similar traffic. Testing is done using

R/S statistic and Variance Time plot method. After analyzed the result from both tools,

the accuracy is more to R/S statistic rather than Variance Time Plot. However, the test

result from data 0.5 shows that VT plot is more accurate rather than R/S statistic because

the result for VT plot is exactly 0.5.

As a conclusion, statistical analysis of the data collected tells us that the selfsimilarity is implementing in the dfgn algorithm.

## Metadata

Item Type: | Thesis (Degree) |
---|---|

Creators: | Creators Email / ID Num. Che Ku Jusoh, Che Ku Noreymie UNSPECIFIED |

Subjects: | Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science |

Divisions: | Universiti Teknologi MARA, Shah Alam > Faculty of Computer and Mathematical Sciences |

Date: | 2006 |

URI: | https://ir.uitm.edu.my/id/eprint/847 |

## Download

TB_CHE KU NOREYMIE CHE KU JUSOH CS 06_5 P01.pdf

Download (110kB) | Preview