Latest revision as of 03:47, 2 February 2021

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). R&D Algoritmi centre

Original document

The different versions of the original document can be found in:

• http://hdl.handle.net/1822/7634

• http://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf

• http://link.springer.com/content/pdf/10.1007/978-3-540-74695-9_46,

http://dx.doi.org/10.1007/978-3-540-74695-9_46

• https://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf,

https://link.springer.com/chapter/10.1007/978-3-540-74695-9_46,

https://dblp.uni-trier.de/db/conf/icann/icann2007-2.html#CortezRSR07,

https://www.scipedia.com/public/Cortez_et_al_2007a,

http://repositorium.sdum.uminho.pt/handle/1822/7634,

https://dl.acm.org/citation.cfm?id=1778118,

http://discovery.ucl.ac.uk/44052,

https://rd.springer.com/chapter/10.1007/978-3-540-74695-9_46,

https://academic.microsoft.com/#/detail/1792912906

• [ ]