DOI QR코드

DOI QR Code

Real-Time Streaming Traffic Prediction Using Deep Learning Models Based on Recurrent Neural Network

순환 신경망 기반 딥러닝 모델들을 활용한 실시간 스트리밍 트래픽 예측

  • Received : 2022.10.04
  • Accepted : 2022.11.14
  • Published : 2023.02.28

Abstract

Recently, the demand and traffic volume for various multimedia contents are rapidly increasing through real-time streaming platforms. In this paper, we predict real-time streaming traffic to improve the quality of service (QoS). Statistical models have been used to predict network traffic. However, since real-time streaming traffic changes dynamically, we used recurrent neural network-based deep learning models rather than a statistical model. Therefore, after the collection and preprocessing for real-time streaming data, we exploit vanilla RNN, LSTM, GRU, Bi-LSTM, and Bi-GRU models to predict real-time streaming traffic. In evaluation, the training time and accuracy of each model are measured and compared.

최근 실시간 스트리밍 플랫폼을 기반으로 한 다양한 멀티미디어 컨텐츠의 수요량과 트래픽 양이 급격히 증가하고 있는 추세이다. 본 논문에서는 실시간 스트리밍 서비스의 품질을 향상시키기 위해서 실시간 스트리밍 트래픽을 예측한다. 네트워크 트래픽을 예측하기 위해 통계적 모형을 활용하였으나, 실시간 스트리밍 트래픽은 매우 동적으로 변화함에 따라 통계적 모형보다는 순환 신경망 기반 딥러닝 모델이 적합하다. 따라서, 실시간 스트리밍 트래픽을 수집, 정제 후 Vanilla RNN, LSTM, GRU, Bi-LSTM, Bi-GRU 모델을 활용하여 예측하며, 각 모델의 학습 시간, 정확도를 측정하여 비교한다.

Keywords

Acknowledgement

이 논문은 2021~2022년도 창원대학교 자율연구과제 연구비 지원으로 수행된 연구결과임. 본 논문은 한국컴퓨터종합학술대회에서 발표된 학부생 논문을 기반으로 확장 및 추가 연구됨.

References

  1. H. Feng and Y. Shu, "Study on network traffic prediction techniques," Proceedings 2005 International Conference on Wireless Communications, Networking and Mobile Computing, pp.1041-1044, 2005.
  2. S. J. Jung, Y. K. Chung, and C. G. Kim, "Network routing by traffic prediction on time series models," Journal of KISS: Information Networking, Vol.32, No.4, pp.433-442, 2005.
  3. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, Vol.9, No.8, pp.1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  4. J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical evaluation of gated recurrent neural networks on sequence modeling," CoRR, abs/1412.3555, 2014.
  5. A. M. Schaefer, S. Udluft, and H. G, Zimmermann, "Learning long-term dependencies with recurrent neural networks," Neurocomputing, Vol.71, No.13-15, pp.2481-2488, 2008. https://doi.org/10.1016/j.neucom.2007.12.036
  6. T. P. Oliveria, J. S. Barbar, and A. S. Soares, "Computer network traffic prediction: A comparison between traditional and deep learning neural networks," International Journal of Big Data Intelligence, Vol.3, No.1, pp.28-37, 2016. https://doi.org/10.1504/IJBDI.2016.073903
  7. P. W. Lee, S. Y. Park, and Y. T. Shin, "Machine learning-based network slicing resource reservation scheme in 5G network," Proceedings of the Korea Information Processing Society Conference, Vol.27, No.1, pp.56-59, 2020.
  8. S. Jaffry and S. F. Hasan, "Cellular traffic prediction using recurrent neural networks," 2020 IEEE 5th International Symposium on Telecommunication Technologies (ISTT), pp.94-98, 2020.
  9. I. G. Lee and M. H. Song, "Leased line traffic prediction using a recurrent deep neural network model," KIPS Transactions on Software and Data Engineering, Vol.10, No.10, pp.391-398,
  10. Y. J. Jang, "Network prediction of traffic generation amount using time series prediction model," Master degree at Hanyang University, 2022.
  11. G. Aceto, G. Bovenzi, D. Ciuonzo, A. Montieri, V. Persico, and A. Pescape, "Characterization and prediction of Mobile-App traffic using markov modeling," IEEE Transactions On Network And Service Management, Vol.18, No.1, pp.907-925,
  12. Wireshark [Internet], https://www.wireshark.org/.
  13. Q. Liu, J. Li, and Z. Lu, "ST-Tran: Spatial-temporal transformer for cellular traffic prediction," in IEEE Communications Letters, Vol.25, No.10, pp.3325-3329, 2021 https://doi.org/10.1109/LCOMM.2021.3098557
  14. D. Aloraifan, I. Ahmad, and E. Alrashed, "Deep learning based network traffic matrix prediction," International Journal of Intelligent Networks, Vol.2, pp.46-56, 2021.  https://doi.org/10.1016/j.ijin.2021.06.002