Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/14482
Título: | Multiscale Internet traffic forecasting using neural networks and time series methods |
Autor(es): | Cortez, Paulo Rio, Miguel Rocha, Miguel Sousa, Pedro |
Palavras-chave: | Network monitoring Multilayer perceptron Time series Traffic engineering |
Data: | 2012 |
Editora: | Wiley-Blackwell |
Revista: | Expert Systems |
Resumo(s): | This article presents three methods to forecast accurately the amount of traffic in TCP=IP based networks: a novel neural network ensemble approach and two important adapted time series methods (ARIMA and Holt-Winters). In order to assess their accuracy, several experiments were held using real-world data from two large Internet service providers. In addition, different time scales (5min, 1h and 1 day) and distinct forecasting lookaheads were analysed. The experiments with the neural ensemble achieved the best results for 5 min and hourly data, while the Holt-Winters is the best option for the daily forecasts. This research opens possibilities for the development of more efficient traffic engineering and anomaly detection tools, which will result in financial gains from better network resource management. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/14482 |
DOI: | 10.1111/j.1468-0394.2010.00568.x |
ISSN: | 0266-4720 |
Versão da editora: | http://dx.doi.org/10.1111/j.1468-0394.2010.00568.x |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals DI/CCTC - Artigos (papers) DSI - Engenharia da Programação e dos Sistemas Informáticos |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
tsf-final.pdf | 353,45 kB | Adobe PDF | Ver/Abrir |