KNOM Review

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Accessing LSTM-based multi-step traffic prediction methods

LSTM 기반 멀티스텝 트래픽 예측 기법 평가

  • Yeom, Sungwoong (Chonnam National University Department of Artificial Intelligence Convergence) ;
  • Kim, Hyungtae (Chonnam National University Department of Artificial Intelligence Convergence) ;
  • Kolekar, Shivani Sanjay (Chonnam National University Department of Artificial Intelligence Convergence) ;
  • Kim, Kyungbaek (Chonnam National University Department of Artificial Intelligence Convergence)
  • Received : 2021.10.15
  • Accepted : 2021.12.01
  • Published : 2021.12.31
⟨ Previous Next ⟩

Abstract

Recently, as networks become more complex due to the activation of IoT devices, research on long-term traffic prediction beyond short-term traffic prediction is being activated to predict and prepare for network congestion in advance. The recursive strategy, which reuses short-term traffic prediction results as an input, has been extended to multi-step traffic prediction, but as the steps progress, errors accumulate and cause deterioration in prediction performance. In this paper, an LSTM-based multi-step traffic prediction method using a multi-output strategy is introduced and its performance is evaluated. As a result of experiments based on actual DNS request traffic, it was confirmed that the proposed LSTM-based multiple output strategy technique can reduce MAPE of traffic prediction performance for non-stationary traffic by 6% than the recursive strategy technique.

최근 IoT 기기들의 활성화에 의해 네트워크가 복잡해짐에 따라, 네트워크의 혼잡을 예측하고 미리 대비하기 위해 단기 트래픽 예측을 넘어 장기 트래픽 예측 연구가 활성화되고 있다. 단기 트래픽 예측 결과를 입력으로 재사용하는 재귀 전략은 멀티 스텝 트래픽 예측으로 확장되었지만, 재귀 단계가 진행될수록 오류가 축적되어 예측 성능 저하를 일으킨다. 이 논문에서는 다중 출력 전략을 사용한 LSTM 기반 멀티스텝 트래픽 예측 기법을 소개하고그 성능을 평가한다. 실제 DNS 요청 트래픽을 기반으로 실험한 결과, 제안된 LSTM기반 다중출력 전략 기법은 재귀 전략 기법에 비해 비정상성 트래픽에 대한 트래픽 예측 성능의 MAPE를 약 6% 줄일 수 있음을 확인하였다.

Keywords

Acknowledgement

"본 연구는 과학기술정보통신부 및 정보통신기획평가원의 대학ICT연구센터육성지원사업의 연구결과로 수행되었음" (IITP-2021-2016-0-00314)

References

  1. Bhuyan, Monowar H., Dhruba Kumar Bhattacharyya, and Jugal K. Kalita. "Network anomaly detection: methods, systems and tools." Ieee communications surveys & tutorials 16.1 (2013): 303-336. https://doi.org/10.1109/SURV.2013.052213.00046
  2. T. Alghamdi, K. Elgazzar, M. Bayoumi, T. Sharaf and S. Shah, "Forecasting Traffic Congestion Using ARIMA Modeling," 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), Tangier, Morocco, 2019, pp. 1227-1232, doi:10.1109/IWCMC.2019.8766698.
  3. R Vinayakumar, KP Soman, and Prabaharan Poornachandran. 2017. Applying deep learning approaches for network traffic prediction. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 2353-2358.
  4. Zang, Chuanyun. "Deep Learning in Multiple Multistep Time Series Prediction." arXiv preprint arXiv:1710.04373 (2017).
  5. Haviluddin, Haviluddin, and Rayner Alfred. "Forecasting network activities using ARIMA method." (2014).
  6. Chan, Kit Yan, et al. "Traffic flow forecasting neural networks based on exponential smoothing method." 2011 6th IEEE Conference on Industrial Electronics and Applications. IEEE, 2011.
  7. Rutka, G. "Network traffic prediction using ARIMA and neural networks models." Elektronika ir Elektrotechnika 84.4 (2008): 53-58.
  8. Somenath Mukherjee, Rajdeep Ray, Rajkumar Samanta, Mofazzal H Khondekar, and Goutam Sanyal. 2017. Nonlinearity and chaos in wireless network traffic. Chaos, Solitons & Fractals 96 (2017), 23-29. https://doi.org/10.1016/j.chaos.2017.01.005
  9. Giang-Truong Nguyen, Van-Quyet Nguyen, Huu-Duy Nguyen, and Kyungbaek Kim. 2018. LSTM based Network Traffic Volume Prediction. In Proceedings of 2018 KIPS Spring Conference.
  10. Giang-Truong Nguyen, Van-Quyet Nguyen, Huu-Duy Nguyen, and Kyungbaek Kim. 2018. LSTM based Network Traffic Volume Prediction. In Proceedings of 2018 KIPS Spring Conference.
  11. H. Lu and F. Yang. 2018. Research on Network Traffic Prediction Based on Long Short-Term Memory Neural Network. In 2018 IEEE 4th International Conference on Computer and Communications (ICCC). 1109-1113.
  12. Cleveland, Robert B., et al. "STL: A seasonal-trend decomposition." J. Off. Stat 6.1 (1990): 3-73.
  13. Siami-Namini, Sima, Neda Tavakoli, and Akbar Siami Namin. "The performance of LSTM and BiLSTM in forecasting time series." 2019 IEEE International Conference on Big Data (Big Data). IEEE, 2019.
  14. Waleed Akbar, Afaq Muhammad, and Wang-Cheol Song, "Analysis of time-series user request pattern dataset for MEC-based video caching scenario", KNOM Review, Vol. 24, No. 1, Aug. 2021, pp. 20-28. https://doi.org/10.22670/KNOM.2021.24.1.20
  15. Min-A Kim and Seung-Joon Seok, "A Study of Virtual IoT System using Edge Computing", KNOM Review, Vol. 23, No. 1, Aug. 2020, pp. 51-62. https://doi.org/10.22670/KNOM.2020.23.1.51
  16. Doyung Lee, Seyon Jeon, Jonghwan Hyun, Jian Li, and James Won-Ki Hong, "Application-aware Traffic Engineering in SDN", KNOM Review, Vol. 19, No. 2, Dec. 2016, pp. 1-12. https://doi.org/10.22670/KNOM.2016.19.2.1
  17. Ntlangu, Mbulelo Brenwen, and Alireza Baghai-Wadji. "Modelling network traffic using time series analysis: A review." Proceedings of the International Conference on Big Data and Internet of Thing. 2017.
  18. Cheng, Changqing, et al. "Time series forecasting for nonlinear and non-stationary processes: a review and comparative study." Iie Transactions 47.10 (2015): 1053-1071. https://doi.org/10.1080/0740817X.2014.999180
  19. F. Pilka and M. Oravec, "Multi-step ahead prediction using neural networks," Proceedings ELMAR-2011, 2011, pp. 269-272.