Paulo Cortez***, Miguel Rio**, Pedro Sousa*, Miguel Rocha*
Universidade do Minho Departamento de Informatica* Departamento de Sistemas de Informacao*** P-4710-057 Braga, Portugal
Tel.: +351 253 604430 |
UCL (University College London)** Department of Computer Science London WC1E 6BT United Kingdom
Tel: +44 20 7679 7214 |
By improving Internet traffic forecasting, more efficient TCP/IP traffic control and anomaly detection tools can be developed, leading to economic gains due to better resource management. In this paper, Neural Networks (NNs) are used to predict TCP/IP traffic for 39 links of the UK education and research network, under univariate and multivariate strategies. The former uses only past values of the forecasted link, while the latter also uses the traffic from neighbor links of the network topology. Several experiments were held by considering hourly real-world data. The Holt-Winters method was also tested in the comparison.
Overall, the univariate NN approach produces the best forecasts for the backbone links, while a Dijkstra based NN multivariate strategy is the best option for the core to subnetwork links.