|
|
Tool for statistical evaluation of the simulation process of JSimlib4 library
Pivoda, Štefan ; Míča, Ivan (oponent) ; Burget, Radim (vedoucí práce)
This master's thesis deals with the analysis of simulation of computer networks. A statistical tool was designed for evaluating a communication between stations in the computer network. JSimlib4 Java library was used for the simulation of computer networks. It is a lightweight but robust simulation library, designed for creating simple or even quite complex simulation models of distributed systems. The Statistical tool was written in Java programming language and developed in an EasyEclipse integrated development environment. It was designed as an Eclipse Rich Client Platform application. Eclipse Rich Client Platform is a relatively new technology, which has a lot of favorable properties. The Statistical tool can be divided into 3 parts: • creating a log file, • creating a filter, • creating/showing an output. The Statistical tool creates records into a log file during every communication between stations. This log file contains a comment on the first line. This comment describes the definition of records. Every record contains 2 IP addresses with the used ports at the beginning of the record, then the time, the amount of bytes, the protocol and the direction of communication. Every item in the record is divided by a colon. The Statistical tool can evaluate a communication between stations. At first, it has to define a filter according to which it will assess the suitable stations. It can be created either by adding IP addresses or names of the stations onto a list on a workbench. Filter can be loaded from a file that already includes these IP addresses and other information too. After defining the filter, the Statistical tool can create either a diagram or a file. At first, the Statistical tool reads the log file line by line and compares the IP addresses, which were added to the filter with the IP addresses in a log file. When the Statistical tool finds a complying IP address, it reads the whole line and adds an amount of bytes defined on that line to the final diagram that is shown after reading the whole log file. In the case of finding 2 or more complying IP addresses that sent the data at the same time, an amount of these transfers is calculated by adding them and this amount is then shown in a diagram. After reading the whole log file a diagram or a file is shown at the bottom of the window. The diagram is created by a Java library JFreechart and it shows the amount of transferred bytes. The x-axis represents the time and the y-axis represents the amount of transferred bytes. The created file is for next work with the calculated data and it can be loaded for example by Matlab or Octave. The first line in the file represents the time for axis x and the second one represents the amount of transferred bytes for axis y. These lines are followed by a command "plot(x,y)" for drawing a diagram.
|
|
|
Tool for statistical evaluation of the simulation process of JSimlib4 library
Pivoda, Štefan ; Míča, Ivan (oponent) ; Burget, Radim (vedoucí práce)
This master's thesis deals with the analysis of simulation of computer networks. A statistical tool was designed for evaluating a communication between stations in the computer network. JSimlib4 Java library was used for the simulation of computer networks. It is a lightweight but robust simulation library, designed for creating simple or even quite complex simulation models of distributed systems. The Statistical tool was written in Java programming language and developed in an EasyEclipse integrated development environment. It was designed as an Eclipse Rich Client Platform application. Eclipse Rich Client Platform is a relatively new technology, which has a lot of favorable properties. The Statistical tool can be divided into 3 parts: • creating a log file, • creating a filter, • creating/showing an output. The Statistical tool creates records into a log file during every communication between stations. This log file contains a comment on the first line. This comment describes the definition of records. Every record contains 2 IP addresses with the used ports at the beginning of the record, then the time, the amount of bytes, the protocol and the direction of communication. Every item in the record is divided by a colon. The Statistical tool can evaluate a communication between stations. At first, it has to define a filter according to which it will assess the suitable stations. It can be created either by adding IP addresses or names of the stations onto a list on a workbench. Filter can be loaded from a file that already includes these IP addresses and other information too. After defining the filter, the Statistical tool can create either a diagram or a file. At first, the Statistical tool reads the log file line by line and compares the IP addresses, which were added to the filter with the IP addresses in a log file. When the Statistical tool finds a complying IP address, it reads the whole line and adds an amount of bytes defined on that line to the final diagram that is shown after reading the whole log file. In the case of finding 2 or more complying IP addresses that sent the data at the same time, an amount of these transfers is calculated by adding them and this amount is then shown in a diagram. After reading the whole log file a diagram or a file is shown at the bottom of the window. The diagram is created by a Java library JFreechart and it shows the amount of transferred bytes. The x-axis represents the time and the y-axis represents the amount of transferred bytes. The created file is for next work with the calculated data and it can be loaded for example by Matlab or Octave. The first line in the file represents the time for axis x and the second one represents the amount of transferred bytes for axis y. These lines are followed by a command "plot(x,y)" for drawing a diagram.
|
host ::
RSS.