Abstract | ||
---|---|---|
Forecasting Internet traffic is receiving an increasing attention from the computer networks domain. Indeed, by improving
this task efficient traffic engineering and anomaly detection tools can be developed, leading to economic gains due to better
resource management. This paper presents a Neural Network (NN) approach to predict TCP/IP traffic for all links of a backbone
network, using both univariate and multivariate strategies. The former uses only past values of the forecasted link, while
the latter is based on the neighbor links of the backbone topology. Several experiments were held by considering real-world
data from the UK education and research network. Also, different time scales (e.g. every ten minutes and hourly) were analyzed.
Overall, the proposed NN approach outperformed other forecasting methods (e.g. Holt-Winters).
|
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-74695-9_46 | ICANN (2) |
Keywords | Field | DocType |
backbone network,forecasting internet traffic,neural network,task efficient traffic engineering,backbone topology,proposed nn approach,topology aware internet traffic,uk education,research network,anomaly detection tool,ip traffic,traffic engineering,network monitoring | Anomaly detection,Data mining,Computer science,Artificial intelligence,Network monitoring,Artificial neural network,Internet traffic,Topology,Internet traffic engineering,Univariate,Backbone network,Traffic engineering,Machine learning | Conference |
Volume | ISSN | ISBN |
4669 | 0302-9743 | 3-540-74693-5 |
Citations | PageRank | References |
2 | 0.40 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paulo Cortez | 1 | 360 | 21.71 |
Miguel Rio | 2 | 277 | 29.40 |
Pedro Sousa | 3 | 174 | 25.25 |
Miguel Rocha | 4 | 511 | 54.06 |