Analysis and modelling of Internet traffic

OData support
Dr. Molnár Sándor
Department of Telecommunications and Media Informatics

My task is to get a knowledge of some models regarding network traffic, to analyse a specific network traffic and to define the values of some bursty and correlational metrics with the help of an already completed traffic measure. First of all, to complete the task, I needed to learn the theoretical background of traffic measure and generation, and to get a better knowledge of some related processes. To do so, I took my telecommunicational, mathematical and statistical knowledge as basis. To define the value of metrics, I used a previously recorded traffic measurement. After I analysed this measure, I searched for a reasonable part of the data to define the final results. The measure contained how many packets arrived at which times. From these data, I mainly used the timestamps. For counting, I mainly used the built-in functions of Matlab and some C++ program codes I wrote myself, but I also used Microsoft Excel and Notepad++ so I could easier work with the data. I defined the values of three metrics: SCV (squared coefficient of variaton), IDI (index of dispersion for intervals) and IDC (index of dispersion for counts). While completing the task, I proved that some of the related definitions are true to the applied traffic. I illustrated the results of the IDI and IDC on different diagrams, analysed them, and further studied the results.


Please sign in to download the files of this thesis.