Neural Network based Network Traffic Predictability for IoT Environment

AUTHORS

Min-Su Seok,Dept. of Computer Science & Engineering, Dongguk Univ., Seoul, Republic of Korea
JinYeong Um*,Dept. of Computer Science & Engineering, Dongguk Univ., Seoul, Republic of Korea

ABSTRACT

The purpose of this paper is to predict of compare network changes using neural networks. Many devices operate for various purposes using network technology, but unmanaged network environments cause packet loss for a variety of reasons. This packet loss causes data retransmissions and delays, and in environment where limited battery or limited network resources must be utilized, various problems can occur. Experiments show how neural networks can be used to predict network changes and whether they can predict changes in real networks. Predictability of Network Traffic indicates that LSTM (Long Short-Term Memory) is higher than MLP (Multi-Layer Perceptron).

 

KEYWORDS

Network prediction, Internet of things, Deep learning, LSTM, MLP, Matlab

REFERENCES

[1]     Yalda E., Jong-Suk A. and Katia O., “Smart experts for network state estimation,” IEEE Transactions on Network and Service Management, vol.13, no.3, pp.622-635, (2016) DOI: 10.1109/TNSM.2016.2586506(CrossRef)(Google Scholar)
[2]     Tiago O, Jami B. and Alexsandro S., “Multilayer perceptron and stacked autoencoder for internet traffic prediction,” 11th IFIP International Conference on Network and Parallel Computing (NPC), pp.61-71, (2014) DOI: 10.1007/978-3-662-44917-2_6(CrossRef)(Google Scholar)
[3]     Robert B. C., William S. C. Jean E. M, and Irma T., “STL: A seasonal-trend decomposition procedure based on loess,” vol.6, no.1, pp.3-73, (1990)
[4]     Sepp H and Jürgen S., “Long short-term memory,” Neural Computation, vol.9, no.8, pp.1735-1780, (1997) DOI: 10.1162/neco.1997.9.8.1735(CrossRef)(Google Scholar)
[5]     Geon-Myeong L., “Artificial intelligence: from turing test to deep learning,” Saeng Neung Publish, (2018)
[6]     Rob J. H., Data Market, https://robjhyndman.com/hyndsight/tsdl/, Jan 1, (2020)
[7]     Haytham M. F., “Mat DL: A lightweight deep learning library in MATLAB,” Journal of Open Source Software, vol.2, no.19, (2017) DOI: 10.21105/joss.00413
[8]     Wei Y., John H., and Deborah E., “An energy-efficient MAC protocol for wireless sensor networks, Proceedings,” Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies, June 23-27; New York, USA, (2002) DOI: 10.1109/INFCOM.2002.1019408(CrossRef)(Google Scholar)

CITATION

  • APA:
    Seok,M.S.& Um*,J.Y.(2020). Neural Network based Network Traffic Predictability for IoT Environment. International Journal of Internet of Things and its Applications, 4(1), 15-22. 10.21742/IJIoTA.2020.4.1.03
  • Harvard:
    Seok,M.S., Um*,J.Y.(2020). "Neural Network based Network Traffic Predictability for IoT Environment". International Journal of Internet of Things and its Applications, 4(1), pp.15-22. doi:10.21742/IJIoTA.2020.4.1.03
  • IEEE:
    [1] M.S.Seok, J.Y.Um*, "Neural Network based Network Traffic Predictability for IoT Environment". International Journal of Internet of Things and its Applications, vol.4, no.1, pp.15-22, Mar. 2020
  • MLA:
    Seok Min-Su and Um* JinYeong. "Neural Network based Network Traffic Predictability for IoT Environment". International Journal of Internet of Things and its Applications, vol.4, no.1, Mar. 2020, pp.15-22, doi:10.21742/IJIoTA.2020.4.1.03

ISSUE INFO

  • Volume 4, No. 1, 2020
  • ISSN(p):2207-4538
  • ISSN(e):2207-4546
  • Published:Mar. 2020

DOWNLOAD