Publicação
Tools for traffic engineering on IP networks
| Resumo: | In this work, an user friendly software application is proposed, built on top of a network optimization framework, aiming to make traffic engineering an easier task for IP network administrators. This framework was developed in the Center of Computer Science and Technology (CCTC) of the University of Minho and allows the improvement of quality of service levels in TCP/IP based networks, by configuring the routing weights of link-state protocols, such as OSPF. This goal is achieved mainly using Evolutionary Algorithms as the optimization engines, while networks are represented using graph-based mathematical models. These methods allow the optimization of distinct cost functions, using penalties that take into account several measures of network performance such as network congestion and average end-to-end delays. The main goal of this work is to create a structured graphical user interface to support the optimization framework, enabling the user to simulate the effects of diferente OSPF settings, to obtain highly optimized configurations and to compare different weight setting optimization methods. |
|---|---|
| Autores principais: | Sá, Tiago |
| Outros Autores: | Rocha, Miguel; Sousa, Pedro |
| Assunto: | Traffic engineering Routing protocols Network management Evolutionary algorithms Open-source software |
| Ano: | 2010 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | In this work, an user friendly software application is proposed, built on top of a network optimization framework, aiming to make traffic engineering an easier task for IP network administrators. This framework was developed in the Center of Computer Science and Technology (CCTC) of the University of Minho and allows the improvement of quality of service levels in TCP/IP based networks, by configuring the routing weights of link-state protocols, such as OSPF. This goal is achieved mainly using Evolutionary Algorithms as the optimization engines, while networks are represented using graph-based mathematical models. These methods allow the optimization of distinct cost functions, using penalties that take into account several measures of network performance such as network congestion and average end-to-end delays. The main goal of this work is to create a structured graphical user interface to support the optimization framework, enabling the user to simulate the effects of diferente OSPF settings, to obtain highly optimized configurations and to compare different weight setting optimization methods. |
|---|