Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/64430
Título: | Deep neural networks for network routing |
Autor(es): | Reis, João Rocha, Miguel Phan, Truong Khoa Griffin, David Le, Franck Rio, Miguel |
Palavras-chave: | Computer networks Neural nets Telecommunication network routing Telecommunication traffic Traffic flows Computer networks Routing decisions Mixed integer linear programming Complex optimization problems Routing framework Deep neural networks Network routing DL model Routing Linear programming Neural networks Internet Optimization Routing protocols |
Data: | 14-Jul-2019 |
Editora: | IEEE |
Revista: | IEEE International Joint Conference on Neural Networks (IJCNN) |
Citação: | Reis, João; Rocha, Miguel; Phan, T. K.; Griffin, D.; Le, F.; Rio, Miguel, Deep Neural Networks for Network Routing. IJCNN 2019 - International Joint Conference on Neural Networks. No. 20199, Budapest, Hungary, July 14-19, 1-8, 2019. |
Resumo(s): | In this work, we propose a Deep Learning (DL) based solution to the problem of routing traffic flows in computer networks. Routing decisions can be made in different ways depending on the desired objective and, based on that objective function, optimal solutions can be computed using a variety of techniques, e.g. with mixed integer linear programming. However, determining these solutions requires solving complex optimization problems and, thus, cannot be typically done at runtime. Instead, heuristics for these problems are often created but designing them is non-trivial in many cases. The routing framework proposed here presents an alternative to the design of heuristics, whilst still achieving good performance. This is done by building a DL model trained on the optimal decisions over flows from known traffic demands. To evaluate our solution, we focused on the problem of network congestion, even though a wide range of alternative objectives could be fitted into this framework. We ran experiments using two publicly available datasets of networks with real traffic demands and showed that our solution achieves close-to-optimal network congestion values. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/64430 |
ISBN: | 978-1-7281-1986-1 |
e-ISBN: | 978-1-7281-1985-4 |
DOI: | 10.1109/IJCNN.2019.8851733 |
ISSN: | 2161-4393 |
Versão da editora: | https://www.ijcnn.org/ |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CEB - Artigos em Livros de Atas / Papers in Proceedings |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
document_53571_1.pdf | 1,14 MB | Adobe PDF | Ver/Abrir |