|
|
Analysis of Parameters of Packet Classification Rule Sets
Sabo, Jozef ; Orsák, Michal (referee) ; Matoušek, Jiří (advisor)
A theme of bachelor's thesis is an analysis of rules used for packet classification in computer networks. A theoretical part of the thesis introduces packet classification and describes the role of classification rules. This part also presents the format of classification rules utilized in real tools. Based on these information, a tool able to analyze IP 5-tuple classification rules in any format was designed and implemented. Output of the implemented tool is a parameter file containing different statistics and probability distributions of examined rule sets. This parameter file can be used for generating synthetic rule sets using ClassBench and ClassBench-ng tools. The final part of the thesis examines parameter files created by the implemented tool from available real rule sets.
|
|
|
Generation of Binary Prefix Tree According to Probabilistic Parameters
Ženčák, Tomáš ; Kučera, Jan (referee) ; Matoušek, Jiří (advisor)
The goal of this work is to create a prefix set generator which will be capable of generating a prefix set from parameters specified in the ClassBench toolset. This work describes a possible approach to generation, as well as the final algorithm for prefix set generation. The resulting generator is able to generate prefix sets whose average deviation from the target parameters is typically orders of magnitude lower than the deviation of sets generated by ClassBench.
|
|
|
Analysis of Parameters of Packet Classification Rule Sets
Sabo, Jozef ; Orsák, Michal (referee) ; Matoušek, Jiří (advisor)
A theme of bachelor's thesis is an analysis of rules used for packet classification in computer networks. A theoretical part of the thesis introduces packet classification and describes the role of classification rules. This part also presents the format of classification rules utilized in real tools. Based on these information, a tool able to analyze IP 5-tuple classification rules in any format was designed and implemented. Output of the implemented tool is a parameter file containing different statistics and probability distributions of examined rule sets. This parameter file can be used for generating synthetic rule sets using ClassBench and ClassBench-ng tools. The final part of the thesis examines parameter files created by the implemented tool from available real rule sets.
|
|
|
Generation of Binary Prefix Tree According to Probabilistic Parameters
Ženčák, Tomáš ; Kučera, Jan (referee) ; Matoušek, Jiří (advisor)
The goal of this work is to create a prefix set generator which will be capable of generating a prefix set from parameters specified in the ClassBench toolset. This work describes a possible approach to generation, as well as the final algorithm for prefix set generation. The resulting generator is able to generate prefix sets whose average deviation from the target parameters is typically orders of magnitude lower than the deviation of sets generated by ClassBench.
|
guest ::
