Cellular Traffic Prediction and Classification: A Comparative Evaluation of LSTM and ARIMA

  • Amin AzariEmail author
  • Panagiotis Papapetrou
  • Stojan Denic
  • Gunnar Peters
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11828)


Prediction of user traffic in cellular networks has attracted profound attention for improving the reliability and efficiency of network resource utilization. In this paper, we study the problem of cellular network traffic prediction and classification by employing standard machine learning and statistical learning time series prediction methods, including long short-term memory (LSTM) and autoregressive integrated moving average (ARIMA), respectively. We present an extensive experimental evaluation of the designed tools over a real network traffic dataset. Within this analysis, we explore the impact of different parameters on the effectiveness of the predictions. We further extend our analysis to the problem of network traffic classification and prediction of traffic bursts. The results, on the one hand, demonstrate the superior performance of LSTM over ARIMA in general, especially when the length of the training dataset is large enough and its granularity is fine enough. On the other hand, the results shed light onto the circumstances in which, ARIMA performs close to the optimal with lower complexity.


Statistical learning Machine learning LSTM ARIMA Cellular traffic Predictive network management 


  1. 1.
    Alawe, I., et al.: Smart scaling of the 5G core network: an RNN-based approach. In: Globecom 2018-IEEE Global Communications Conference, pp. 1–6 (2018)Google Scholar
  2. 2.
    Assem, H., Caglayan, B., Buda, T.S., O’Sullivan, D.: ST-DenNetFus: a new deep learning approach for network demand prediction. In: Brefeld, U., et al. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11053, pp. 222–237. Springer, Cham (2019). Scholar
  3. 3.
    Azari, A.: Cellular traffic analysis (2019).
  4. 4.
    Azari, A., Cavdar, C.: Self-organized low-power IoT networks: a distributed learning approach. In: IEEE Globecom 2018 (2018)Google Scholar
  5. 5.
    Azari, A., et al.: Risk-aware resource allocation for URLLC: challenges and strategies with machine learning. IEEE Commun. Mag. 57, 42–48 (2019)CrossRefGoogle Scholar
  6. 6.
    Azzouni, A., Pujolle, G.: NeuTM: a neural network-based framework for traffic matrix prediction in SDN. In: NOMS 2018–2018 IEEE/IFIP Network Operations and Management Symposium, pp. 1–5 (2018)Google Scholar
  7. 7.
    Box, G.E., Jenkins, G.M.: Time Series Analysis: Forecasting and Control, Revised edn. Holden-Day, San Francisco (1976)zbMATHGoogle Scholar
  8. 8.
    Brockwell, P.J., Davis, R.A., Calder, M.V.: Introduction to Time Series and Forecasting, vol. 2. Springer, New York (2002). Scholar
  9. 9.
    Chen, M., et al.: Machine learning for wireless networks with artificial intelligence: a tutorial on neural networks. arXiv preprint arXiv:1710.02913 (2017)
  10. 10.
    Chen, T., et al.: Multivariate arrival times with recurrent neural networks for personalized demand forecasting. arXiv preprint arXiv:1812.11444 (2018)
  11. 11.
    Cho, K., van Merrienboer, B., Gülçehre, Ç., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR abs/1406.1078 (2014).
  12. 12.
    Choi, H.K.: Stock price correlation coefficient prediction with ARIMA-LSTM hybrid model. arXiv preprint arXiv:1808.01560 (2018)
  13. 13.
    Huang, C.W., Chiang, C.T., Li, Q.: A study of deep learning networks on mobile traffic forecasting. In: 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), pp. 1–6 (2017)Google Scholar
  14. 14.
    Lai, G., Chang, W.C., Yang, Y., Liu, H.: Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 95–104 (2018)Google Scholar
  15. 15.
    Li, R., et al.: The prediction analysis of cellular radio access network traffic. IEEE Commun. Mag. 52(6), 234–240 (2014)CrossRefGoogle Scholar
  16. 16.
    Lopez-Martin, M., Carro, B., Sanchez-Esguevillas, A., Lloret, J.: Network traffic classifier with convolutional and recurrent neural networks for internet of things. IEEE Access 5, 18042–18050 (2017)CrossRefGoogle Scholar
  17. 17.
    Mills, T.C.: Time Series Techniques for Economists. Cambridge University Press, New York (1991)zbMATHGoogle Scholar
  18. 18.
    Qiu, C., Zhang, Y., Feng, Z., Zhang, P., Cui, S.: Spatio-temporal wireless traffic prediction with recurrent neural network. IEEE Wirel. Commun. Lett. 7(4), 554–557 (2018)CrossRefGoogle Scholar
  19. 19.
    Rebane, J., Karlsson, I., Denic, S., Papapetrou, P.: Seq2seq RNNs and ARIMA Models for cryptocurrency Prediction: A Comparative Study (2018)Google Scholar
  20. 20.
    Rezaei, S., Liu, X.: Deep learning for encrypted traffic classification: an overview. arXiv preprint arXiv:1810.07906 (2018)
  21. 21.
    Rubinstein, R.Y., Kroese, D.P.: Simulation and the Monte Carlo Method, vol. 10. Wiley, New York (2016)CrossRefGoogle Scholar
  22. 22.
    Saad, W., et al.: A vision of 6G wireless systems: applications, trends, technologies, and open research problems. arXiv preprint arXiv:1902.10265 (2019)
  23. 23.
    Skehin, T., et al.: Day ahead forecasting of FAANG stocks using ARIMA, LSTM networks and wavelets. In: CEUR Workshop Proceedings (2018)Google Scholar
  24. 24.
    Tealab, A.: Time series forecasting using artificial neural networks methodologies. Future Comput. Inf. J. 3(2), 334–340 (2018)CrossRefGoogle Scholar
  25. 25.
    Tong, V., Tran, H.A., Souihi, S., Melouk, A.: A novel QUIC traffic classifier based on convolutional neural networks. In: IEEE International Conference on Global Communications (GlobeCom), pp. 1–6 (2018)Google Scholar
  26. 26.
    Trinh, H.D., Giupponi, L., Dini, P.: Mobile traffic prediction from raw data using LSTM networks. In: 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), pp. 1827–1832 (2018)Google Scholar
  27. 27.
    Wang, J., et al.: Spatio-temporal modeling and prediction in cellular networks: a big data enabled deep learning approach. In: IEEE Conference on Computer Communications, pp. 1–9 (2017)Google Scholar
  28. 28.
    Wang, K., et al.: Modeling and optimizing the LTE discontinuous reception mechanism under self-similar traffic. IEEE Trans. Veh. Tech. 65(7), 5595–5610 (2016)CrossRefGoogle Scholar
  29. 29.
    Williams, N., Zander, S., Armitage, G.: A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. ACM SIGCOMM Comput. Commun. Rev. 36(5), 5–16 (2006)CrossRefGoogle Scholar
  30. 30.
    Ye, J., Zhang, Y.J.A.: DRAG: Deep reinforcement learning based base station activation in heterogeneous networks. arXiv preprint arXiv:1809.02159 (2018)
  31. 31.
    Zhang, G.P.: Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)CrossRefGoogle Scholar
  32. 32.
    Zhang, Q., et al.: Machine learning for predictive on-demand deployment of UAVs for wireless communications. arXiv preprint arXiv:1805.00061 (2018)
  33. 33.
    Zhang, Y., Årvidsson, A.: Understanding the characteristics of cellular data traffic. In: Proceedings of the 2012 ACM SIGCOMM Workshop on Cellular Networks: Operations, Challenges, and Future Design, pp. 13–18 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Amin Azari
    • 1
    Email author
  • Panagiotis Papapetrou
    • 1
  • Stojan Denic
    • 2
  • Gunnar Peters
    • 2
  1. 1.Department of Computer and Systems SciencesStockholm UniversityStockholmSweden
  2. 2.HuaweiStockholmSweden

Personalised recommendations