(Created page with " == Abstract == Forecasting Internet traffic is receiving an increasing attention from the computer networks domain. Indeed, by improving this task efficient traffic engineer...") |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
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 | 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 | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| Line 17: | Line 12: | ||
* [http://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf http://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf] | * [http://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf 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://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 http://dx.doi.org/10.1007/978-3-540-74695-9_46] | ||
| + | |||
| + | * [https://repositorium.sdum.uminho.pt/bitstream/1822/7634/1/forecast.pdf 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://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://dblp.uni-trier.de/db/conf/icann/icann2007-2.html#CortezRSR07], | ||
| + | : [https://www.scipedia.com/public/Cortez_et_al_2007a https://www.scipedia.com/public/Cortez_et_al_2007a], | ||
| + | : [http://repositorium.sdum.uminho.pt/handle/1822/7634 http://repositorium.sdum.uminho.pt/handle/1822/7634], | ||
| + | : [https://dl.acm.org/citation.cfm?id=1778118 https://dl.acm.org/citation.cfm?id=1778118], | ||
| + | : [http://discovery.ucl.ac.uk/44052 http://discovery.ucl.ac.uk/44052], | ||
| + | : [https://rd.springer.com/chapter/10.1007/978-3-540-74695-9_46 https://rd.springer.com/chapter/10.1007/978-3-540-74695-9_46], | ||
| + | : [https://academic.microsoft.com/#/detail/1792912906 https://academic.microsoft.com/#/detail/1792912906] | ||
| + | |||
| + | * [ ] | ||
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:
- 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
- [ ]
Back to Top
Document information
Published on 01/01/2007
Volume 2007, 2007
DOI: 10.1007/978-3-540-74695-9_46
Licence: CC BY-NC-SA license
Share this document
Keywords
Anomaly detection • Artificial intelligence • Artificial neural network • Backbone network • Computer science • Data mining • Internet traffic • Internet traffic engineering • Link mining • Machine learning • Multilayer perceptrons • Multivariate time series • Network monitoring • Science & Technology • Topology • Traffic engineering
claim authorship
Are you one of the authors of this document?