|
|
Prediction of data flow in computer networks
Zvěřina, Lukáš ; Sobek, Jiří (referee) ; Vychodil, Petr (advisor)
The aim of this thesis was to study problems of prediction of data in computer networks. Furthermore, this work deals with network traffic and analyzing its properties. In this study were analyzed the possibilities of network traffic prediction using Farima model, the theory of chaos with Lyapunov exponents and neural networks. Possibilities of prediction with the focus on neural network were discussed in detail here, mainly on recurrent neural networks. Prediction was performed in Matlab development environment in Neural Network Toolbox, where they were created, trained and evaluated neural network to predict specific types of network traffic. For testing were selected Elman network NARX network and general LRN recurrent network. The results were clearly organized into tables and plotted in graphical relationships before and after the use of predictive techniques designed to final evaluation.
|
|
|
Triple Play simulations for next generation networks
Sikora, Pavel ; Polák, Josef (referee) ; Horváth, Tomáš (advisor)
This thesis deals with XG-PON networks. It describes the parameters of the physical layer, its divisions and the branching possibilities. It also describes the transfer layer and its sublayers, discloses the activation process of ONU units when ONU unit connected to ODN. Finally, the thesis describes DBA algorithm including a detailed representation of a DBA algorithm reference model and a representation of the two DBA algorithms implemented in practice. Simulations of Triple Play services in the network with software NS-3 are also included. Simulations using simple DBA algorithm and GIANT algorithm. Thesis contains too modification of GIANT DBA decreasing data trasfer delay.
|
|
|
Triple Play simulations for next generation networks
Sikora, Pavel ; Polák, Josef (referee) ; Horváth, Tomáš (advisor)
This thesis deals with XG-PON networks. It describes the parameters of the physical layer, its divisions and the branching possibilities. It also describes the transfer layer and its sublayers, discloses the activation process of ONU units when ONU unit connected to ODN. Finally, the thesis describes DBA algorithm including a detailed representation of a DBA algorithm reference model and a representation of the two DBA algorithms implemented in practice. Simulations of Triple Play services in the network with software NS-3 are also included. Simulations using simple DBA algorithm and GIANT algorithm. Thesis contains too modification of GIANT DBA decreasing data trasfer delay.
|
|
|
Prediction of data flow in computer networks
Zvěřina, Lukáš ; Sobek, Jiří (referee) ; Vychodil, Petr (advisor)
The aim of this thesis was to study problems of prediction of data in computer networks. Furthermore, this work deals with network traffic and analyzing its properties. In this study were analyzed the possibilities of network traffic prediction using Farima model, the theory of chaos with Lyapunov exponents and neural networks. Possibilities of prediction with the focus on neural network were discussed in detail here, mainly on recurrent neural networks. Prediction was performed in Matlab development environment in Neural Network Toolbox, where they were created, trained and evaluated neural network to predict specific types of network traffic. For testing were selected Elman network NARX network and general LRN recurrent network. The results were clearly organized into tables and plotted in graphical relationships before and after the use of predictive techniques designed to final evaluation.
|
guest ::
