Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/28693
Autoria: | Santana, P. Moura, J. |
Data: | 2023 |
Título próprio: | A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards |
Título da revista: | Algorithms |
Volume: | 16 |
Número: | 5 |
Referência bibliográfica: | Santana, P., & Moura, J. (2023). A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards. Algorithms, 16(5), 233. http://dx.doi.org/10.3390/a16050233 |
ISSN: | 1999-4893 |
DOI (Digital Object Identifier): | 10.3390/a16050233 |
Palavras-chave: | Networks Routing Congestion Variable link delay SDN Algorithm design Multi-armed bandits |
Resumo: | To handle the exponential growth of data-intensive network edge services and automatically solve new challenges in routing management, machine learning is steadily being incorporated into software-defined networking solutions. In this line, the article presents the design of a piecewise-stationary Bayesian multi-armed bandit approach for the online optimum end-to-end dynamic routing of data flows in the context of programmable networking systems. This learning-based approach has been analyzed with simulated and emulated data, showing the proposal’s ability to sequentially and proactively self-discover the end-to-end routing path with minimal delay among a considerable number of alternatives, even when facing abrupt changes in transmission delay distributions due to both variable congestion levels on path network devices and dynamic delays to transmission links. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | ISTAR-RI - Artigos em revistas científicas internacionais com arbitragem científica IT-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
article_95797.pdf | 582,65 kB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.