Multilayer Perceptron and Stacked Autoencoder for Internet Traffic Prediction

  • Tiago Prado Oliveira
  • Jamil Salem Barbar
  • Alexsandro Santos Soares
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8707)


Internet traffic prediction is an important task for many applications, such as adaptive applications, congestion control, admission control, anomaly detection and bandwidth allocation. In addition, efficient methods of resource management can be used to gain performance and reduce costs. The popularity of the newest deep learning methods has been increasing in several areas, but there is a lack of studies concerning time series prediction. This paper compares two different artificial neural network approaches for the Internet traffic forecast. One is a Multilayer Perceptron (MLP) and the other is a deep learning Stacked Autoencoder (SAE). It is shown herein how a simpler neural network model, such as the MLP, can work even better than a more complex model, such as the SAE, for Internet traffic prediction.


Internet traffic time series prediction forecasting neural network machine learning multilayer perceptron deep learning stacked autoencoder 


  1. 1.
    Han, M.-S.: Dynamic bandwidth allocation with high utilization for XG-PON. In: 16th International Conference on Advanced Communication Technology (ICACT), pp. 994–997. IEEE (2014)Google Scholar
  2. 2.
    Zhao, H., Niu, W., Qin, Y., Ci, S., Tang, H., Lin, T.: Traffic Load-Based Dynamic Bandwidth Allocation for Balancing the Packet Loss in DiffServ Network. In: 11th International Conference on Computer and Information Science (ICIS), pp. 99–104. IEEE/ACIS (2012)Google Scholar
  3. 3.
    Liang, Y., Han, M.: Dynamic Bandwidth Allocation Based on Online Traffic Prediction for Real-Time MPEG-4 Video Streams. EURASIP Journal on Advances in Signal Processing (2007)Google Scholar
  4. 4.
    Nguyen, T.D., Eido, T., Atmaca, T.: An Enhanced QoS-enabled Dynamic Bandwidth Allocation Mechanism for Ethernet PON. In: International Conference on Emerging Network Intelligence, pp. 135–140. EMERGING (2009)Google Scholar
  5. 5.
    Cortez, P., Rio, M., Rocha, M., Sousa, P.: Multi-scale Internet traffic forecasting using neural networks and time series methods. ExpertSystems: The Journal of Knowledge Engineering 29, 143–155 (2012)Google Scholar
  6. 6.
    Hallas, M., Dorffner, G.: A comparative study of feedforward and recurrent neural networks in time series prediction. In: 14th European Meet. Cybernetics Systems Research, vol. 2, pp. 644–647 (1998)Google Scholar
  7. 7.
    Ding, X., Canu, S., Denoeux, T.: Neural Network Based Models for Forecasting. In: Proceedings of Applied Decision Technologies (ADT 1995), pp. 243–252. Wiley and Sons, Uxbridge (1995)Google Scholar
  8. 8.
    Feng, H., Shu, Y.: Study on network traffic prediction techniques. In: International Conference on Wireless Communications, Networking and Mobile Computing, vol. 2, pp. 1041–1044. WiCOM (2005)Google Scholar
  9. 9.
    Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2, 1–127 (2009)CrossRefzbMATHGoogle Scholar
  10. 10.
    Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  11. 11.
    Hyndman, R.J.: Time Series Data Library,
  12. 12.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall PTR, Upper Saddle River (1998)Google Scholar
  13. 13.
    Erhan, D., Manzagol, P.-A., Bengio, Y., Bengio, S., Vincent, P.: The difficulty of training deep architectures and the effect of unsupervised pre-training. In: Proceedings of The Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), pp. 153–160 (2009)Google Scholar
  14. 14.
    Villiers, J., Barnard, E.: Backpropagation neural nets with one and two hidden layers. IEEE Transactions on Neural Networks 4, 136–141 (1993)CrossRefGoogle Scholar
  15. 15.
    Hornik, K., Stinchcombe, M., White, H.: Multi- layer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)CrossRefGoogle Scholar
  16. 16.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and Composing Robust Features with Denoising Autoencoders. In: Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML 2008), pp. 1096–1103. ACM, New York (2008)Google Scholar
  17. 17.
    Unsupervised Feature Learning and Deep Learning. Stanford’s online wiki. Stacked Autoencoders,
  18. 18.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Schlkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems 19 (NIPS 2006), pp. 153–160. MIT Press (2007)Google Scholar
  19. 19.
    Larochelle, H., Erhan, D., Vincent, P.: Deep learning using robust interdependent codes. In: Dyk, D.V., Welling, M. (eds.) Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), vol. 5, pp. 312–319 (2009); Journal of Machine Learning Research - Proceedings Track (2009)Google Scholar
  20. 20.
    Ranzato, M.A., Boureau, Y.-L., LeCun, Y.: Sparse Feature Learning for Deep Belief Networks. In: Platt, J., Koller, D., Singer, Y., Roweis, S. (eds.) Advances in Neural Information Processing Systems 20, pp. 1185–1192. MIT Press, Cambridge (2007)Google Scholar
  21. 21.
    Palm, R.B.: DeepLearnToolbox, a Matlab toolbox for Deep Learning,
  22. 22.
    Busseti, E., Osband, I., Wong, S.: Deep Learning for Time Series Modeling. Stanford, CS 229: Machine Learning (2012)Google Scholar
  23. 23.
    Arel, I., Rose, D.C., Karnowski, T.P.: Deep Machine Learning - A New Frontier in Artificial Intelligence Research [research frontier]. IEEE Computational Intelligence Magazine 5, 13–18 (2010)CrossRefGoogle Scholar
  24. 24.
    Chao, J., Shen, F., Zhao, J.: Forecasting exchange rate with deep belief networks. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 1259–1266 (2011)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2014

Authors and Affiliations

  • Tiago Prado Oliveira
    • 1
  • Jamil Salem Barbar
    • 1
  • Alexsandro Santos Soares
    • 1
  1. 1.Faculty of Computer ScienceFederal University of UberlândiaUberlândiaBrazil

Personalised recommendations