Internet Traffic Forecasting using Neural Networks
Open accessAbstract
The forecast of Internet traffic is an important issue that has received few attention from the computer networks field. By improving this task, efficient traffic engineering and anomaly detection tools can be created, resulting in economic gains from better resource management. This paper presents a neural network ensemble (NNE) for the prediction of TCP/IP traffic using a time series forecasting (TSF) point of view. Several experiments were devised by considering real-world data from two large Internet Service Providers. In addition, different time scales (e.g. every five minutes and hourly) and forecasting horizons were analyzed. Overall, the NNE approach is competitive when compared with other TSF methods (e.g. Holt-Winters and ARIMA).
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The comparison amongst the TSF methods shows that in general the NNE produces the lowest MAPE for both datasets.
“The comparison amongst the TSF methods show that in general the NNE produces the lowest MAPE for both datasets.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [104]
It also shows that in terms of time and computational complexity, NNE outperforms the other methods with an order of magnitude, and is well suited for real-time forecasting.
“It also shows that in terms of time and computational complexity, NNE outperforms the other methods with an order of magnitude, and is well suited for real-time forecasting.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [104]
Cortez et al. use a NN ensemble (NNE) of five MLP-NN with one hidden layer each, trained with Resilient backpropagation on SNMP traffic data collected from two different ISP networks.
“Cortez et al. [104] choose to use a NN ensemble (NNE) of five MLP-NN with one hidden layer each.Resilient backpropagation (Rp) training is used on SNMP traffic data collected from two different ISP networks.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [104]
TSF approaches, such as [52, 86, 104, 141, 500], where NNs are used to infer traffic volumes from past measured volumes, show high long-term and short-term prediction accuracy at low complexity with limited number of features and limited number of layers and neurons.
“TSF approaches, such as [52, 86, 104, 141, 500], where NNs are used to infer traffic volumes from past measured volumes, show high long-term and short-term prediction accuracy at low complexity with limited number of features and limited number of layers and neurons.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [104]
Cites
Book Review: Time Series Analysis: Forecasting and Control
Geurts, M. D., Box, G. E. P., & Jenkins, G. M. (1977) · Journal of Marketing Research · doi:10.2307/3150485 · Cited by 19,399 · see citing works
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
Lu, Z. Q. J. (2010) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,904 · see citing works
Ensemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408 · see citing works
Forecasting Sales by Exponentially Weighted Moving Averages
Winters, P. R. (1960) · Management Science · doi:10.1287/mnsc.6.3.324 · Cited by 2,132 · see citing works
Short-term electricity demand forecasting using double seasonal exponential smoothing
Taylor, J. W. (2003) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2601589 · Cited by 750 · see citing works
New Capabilities and Methods of the X-12-ARIMA Seasonal-Adjustment Program
Findley, D. F., Monsell, B. C., Bell, W. R., Otto, M. C., & Chen, B.-C. (1998) · Journal of Business and Economic Statistics · doi:10.1080/07350015.1998.10524743 · Cited by 673 · see citing works
Forecasting: Methods and Applications
Briggs, W. M., Makridakis, S., Wheelwright, S. C., Hyndman, R. J., & Diebold, F. X. (1999) · Journal of the American Statistical Association · doi:10.2307/2669717 · Cited by 626 · see citing works
Riedmiller, M. (1994) · Computer Standards & Interfaces · doi:10.1016/0920-5489(94)90017-5 · Cited by 604 · see citing works
Krishnamurthy, B., Sen, S. B., Zhang⋆, Y., & Chen, Y. (2003) · ACM Internet Measurement Conference (IMC) · doi:10.1145/948205.948236 · Cited by 528 · see citing works
A comparison of univariate methods for forecasting electricity demand up to a day ahead
Taylor, J. W., de Menezes, L. M., & McSharry, P. (2005) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2005.06.006 · Cited by 490 · see citing works
Nonlinear signal processing using neural networks: Prediction and system modelling
Lapedes, A. S., & Farber, R. M. (1987) · University of North Texas Digital Library (University of North Texas) · Cited by 373 · see citing works
SNMP, SNMPv2, SNMPv3, and RMON 1 and 2
Stallings, W. (1998) · Medical Entomology and Zoology · Cited by 333 · see citing works
Particle swarms for feedforward neural network training
Mendes, R., Cortez, P., Rocha, M., et al. (2003) · doi:10.1109/ijcnn.2002.1007808 · Cited by 276 · see citing works
Self-citationA predictability analysis of network traffic
Sang, A., & Li, S.-Q. (2002) · Computer Networks · doi:10.1016/s1389-1286(01)00304-8 · Cited by 248 · see citing works
Data mining and the impact of missing data
Brown, M. L., & Kros, J. F. (2003) · Industrial Management & Data Systems · doi:10.1108/02635570310497657 · Cited by 181 · see citing works
On the predictability of large transfer TCP throughput
He, Q., Dovrolis, C., & Ammar, M. (2005) · ACM SIGCOMM Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM) · doi:10.1145/1080091.1080110 · Cited by 163 · see citing works
Long-Term Forecasting of Internet Backbone Traffic
Papagiannaki, K., Taft, N., Zhang, Z.-L., & Diot, C. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.853437 · Cited by 150 · see citing works
Evolving Time Series Forecasting ARMA Models
Cortez, P., Rocha, M., & Neves, J. (2004) · Journal of Heuristics · doi:10.1023/b:heur.0000034714.09838.1e · Cited by 90 · see citing works
Self-citationDetecting Network Attacks in the Internet via Statistical Network Traffic Normality Prediction
Jiang, J., & Papavassiliou, S. (2004) · Journal of Network and Systems Management · doi:10.1023/b:jons.0000015698.32353.61 · Cited by 50 · see citing works
Applications of nonlinear prediction methods to the Internet traffic
Hasegawa, M., Wu, G., & Mizuni, M. (2002) · doi:10.1109/iscas.2001.921273 · Cited by 41 · see citing works
Time Series Forecasting by Evolutionary Neural Networks
Cortez, P., Rocha, M., & Neves, J. (2006) · IGI Global eBooks · doi:10.4018/978-1-59140-902-1.ch003 · Cited by 26 · see citing works
Self-citationBoosting feed-forward neural network for internet traffic prediction
Tong, H., Li, C., & He, J.-R. (2005) · doi:10.1109/icmlc.2004.1378572 · Cited by 16 · see citing works
An artificial neural network-genetic based approach for time series forecasting
Neves, J., & Cortez, P. (2002) · Proceedings - Brazilian Symposium on Neural Networks/Proceedings of the ... Brazilian Symposium on Neural Networks · doi:10.1109/sbrn.1997.645842 · Cited by 8 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., & Caicedo, O. M. (2018) · Journal of Internet Services and Applications · doi:10.1186/s13174-018-0087-2 · Cited by 1,036 · see citing works
Karami, A. (2015) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2015.05.017 · Cited by 29 · see citing works
- Authors
- Cortez, P., Rio, M., Rocha, M., & Sousa, P.
- Affiliations
- University of Minho (PT)
- Venue
- The 2006 IEEE International Joint Conference on Neural Network Proceedings
- Publisher
- IEEE
- Published
- 2006
- Pages
- 2635-2642
- ISSN
- 2161-4407 (ISSN-L)
- OpenAlex
- W2017528563
- Cited by
- 118
- References
- 23
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 5 · 2023: 5 · 2022: 9 · 2021: 13 · 2020: 15 · 2019: 3 · 2018: 11 · 2017: 9 · 2016: 4 · 2015: 7 · 2014: 7 · 2013: 3 · 2012: 3
- FWCI
- 3.58
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- Locations
- International Joint Conference on Neural Networks (IJCNN) (publishedVersion)
- Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion, other-oa)
- UCL Discovery (University College London) (submittedVersion)
- Funders
- Nuffield Foundation
- Engineering and Physical Sciences Research Council
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Physical Sciences › Engineering › Building and Construction › Traffic Prediction and Management Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Keywords
- neural network ensembles, time series forecasting, traffic engineering, anomaly detection, internet service providers, forecast horizon, Holt-Winters, ARIMA
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
