|
|
Network Traffic Generator for Testing of Packet Classification Algorithms
Janeček, David ; Orsák, Michal (oponent) ; Matoušek, Jiří (vedoucí práce)
Efforts to improve classification algorithms are being slowed down by lack of data required for testing. For confidentiality and security reasons it is difficult to obtain real data. Good rule set generation tools, such as ClassBench-ng, exist. However, in order to evaluate proper functioning, throughput, power consumption, and other properties of packet classification algorithms, it is necessary to also use network traffic. Subject of this thesis is creating a network traffic generator that would allow for testing of such properties using IPv4, IPv6, and OpenFlow1.0 rules created by ClassBench-ng. The work explores different ways to achieve this, which resulted in several versions of the generator. Those were experimented with and evaluated. Implementation was done using Python. The primary result is a generator combining multiple approaches to achieve the best properties of created header traces. Another contribution of this thesis is a tool that was necessary to create for analyzing rule sets and evaluating generated header traces.
|
|
|
Network Traffic Generator for Testing of Packet Classification Algorithms
Janeček, David ; Orsák, Michal (oponent) ; Matoušek, Jiří (vedoucí práce)
Efforts to improve classification algorithms are being slowed down by lack of data required for testing. For confidentiality and security reasons it is difficult to obtain real data. Good rule set generation tools, such as ClassBench-ng, exist. However, in order to evaluate proper functioning, throughput, power consumption, and other properties of packet classification algorithms, it is necessary to also use network traffic. Subject of this thesis is creating a network traffic generator that would allow for testing of such properties using IPv4, IPv6, and OpenFlow1.0 rules created by ClassBench-ng. The work explores different ways to achieve this, which resulted in several versions of the generator. Those were experimented with and evaluated. Implementation was done using Python. The primary result is a generator combining multiple approaches to achieve the best properties of created header traces. Another contribution of this thesis is a tool that was necessary to create for analyzing rule sets and evaluating generated header traces.
|
host ::
RSS.