KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Leased Line Traffic Prediction Using a Recurrent Deep Neural Network Model

순환 심층 신경망 모델을 이용한 전용회선 트래픽 예측

  • Received : 2021.06.29
  • Accepted : 2021.08.11
  • Published : 2021.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Since the leased line is a structure that exclusively uses two connected areas for data transmission, a stable quality level and security are ensured, and despite the rapid increase in the number of switched lines, it is a line method that is continuously used a lot in companies. However, because the cost is relatively high, one of the important roles of the network operator in the enterprise is to maintain the optimal state by properly arranging and utilizing the resources of the network leased line. In other words, in order to properly support business service requirements, it is essential to properly manage bandwidth resources of leased lines from the viewpoint of data transmission, and properly predicting and managing leased line usage becomes a key factor. Therefore, in this study, various prediction models were applied and performance was evaluated based on the actual usage rate data of leased lines used in corporate networks. In general, the performance of each prediction was measured and compared by applying the smoothing model and ARIMA model, which are widely used as statistical methods, and the representative models of deep learning based on artificial neural networks, which are being studied a lot these days. In addition, based on the experimental results, we proposed the items to be considered in order for each model to achieve good performance for prediction from the viewpoint of effective operation of leased line resources.

전용회선은 데이터 전송에 있어서 연결된 두 지역을 독점적으로 사용하는 구조이기 때문에 안정된 품질수준과 보안성이 확보되어 교환회선의 급격한 증가에도 불구하고 기업 내부에서는 지속적으로 많이 사용하는 회선 방식이다. 하지만 비용이 상대적으로 고가이기 때문에 기업 내 네트워크 운영자의 중요한 역할 중의 하나는 네트워크 전용회선의 자원을 적절히 배치하고 활용하여 최적의 상태를 유지하는 것이 중요한 요소이다. 즉, 비즈니스 서비스 요구 사항을 적절히 지원하기 위해서는 데이터 전송 관점에서 전용회선의 대역폭 자원에 대한 적절한 관리가 필수적이며 전용회선 사용량을 적절히 예측하고 관리하는 것이 핵심 요소가 된다. 이에 본 연구에서는 기업 네트워크에서 사용하는 전용회선의 실제 사용률 데이터를 기반으로 다양한 예측 모형을 적용하고 성능을 평가하였다. 일반적으로 통계적인 방법으로 많이 사용하는 평활화 기법 및 ARIMA 모형과 요즘 많은 연구가 되고 있는 인공신경망에 기반한 딥러닝의 대표적인 모형들을 적용하여 각각의 예측에 대한 성능을 측정하고 비교하였다. 또한, 실험결과에 기초하여 전용회선 자원의 효과적인 운영 관점에서 각 모형이 예측에 대하여 좋은 성능을 내기 위하여 고려해야 할 사항을 제안하였다.

Keywords

References

  1. I. G. Lee and M. H. Song, "A comparative study of statistical techniques and machine learning models for efficient leased line resource usage prediction," Proceedings of the KIPS, Vol.28., No.1, pp.474-476, 2021.
  2. L. G. Roberts and B. D. Wessler, "Computer network development to achieve resource sharing," Proceedings of the May 5-7, 1970, Spring Joint Computer Conference, 1970.
  3. H. M. Sigurdsson, S. E. Thorsteinsson, and T. K. Stidsen. "Cost optimization methods in the design of next generation networks," IEEE Communications Magazine, Vol.42, No.9, pp.118-122, 2004.
  4. Statistical Office, "Business Basic Statistical Survey Report," Each Year (2020).
  5. M. Joshi and T. H. Hadi, "A review of network traffic analysis and prediction techniques," arXiv preprint arXiv: 1507.05722, 2015.
  6. W. Yoo and A. Sim. "Time-series forecast modeling on high-bandwidth network measurements," Journal of Grid Computing, Vol.14, No.3, pp.463-476, 2016. https://doi.org/10.1007/s10723-016-9368-9
  7. H. W. Taek, A. S. Jin, and C. J. Wook, "Forecasting technique of line utilization based on SNMP MIB-II using time series analysis," KIPS Journal, Vol.6, No.9, pp.2470-2478, 1999. DOI: 10.3745/KIPSTE.1999.6.9.2470.
  8. S. J. Jung, D. J. Kim, Y. H. Know, and C. G. Kim, "A fitness verification of time series models for network traffic predictions," The Journal of Korea Information and Communications Society, Vol.29, No.2B, pp.217-227, 2004.
  9. S. H. Ji, H. Hasanova, K. S. Shim, and M. S. Kim, "Prediction of traffic usage using machine learning algorithm for efficient network management," Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.824-825, 2018.
  10. W. Stallings, "SNMP and SNMPv2: the infrastructure for network management," IEEE Communications Magazine, Vol.36, No.3, pp.37-43, 1998. https://doi.org/10.1109/35.663326
  11. J. D. Case, M. Fedor, M. L., Schoffstall, and J. Davin, "RFC1157: Simple network management protocol (snmp)," 1990.
  12. K. McCloghrie and M. T. Rose, "RFC1213: Management information base for network management of TCP/IP-based internets: MIB-II," 1991.
  13. M. T. Rose and K. McCloghrie, "RFC1155: Structure and identification of management information for TCP/IP-based internets," 1990.
  14. R. G. Brown and R. F. Meyer, "The fundamental theorem of exponential smoothing," Operations Research, Vol.9, No.5, pp.673-685, 1961. https://doi.org/10.1287/opre.9.5.673
  15. G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, "Time series analysis: Forecasting and control," John Wiley & Sons, 2015.
  16. R. J. Hyndman and G. Athanasopoulos, "Forecasting: Principles and practice," OTexts, 2018. [Internet], Available from: https://otexts.com/fpp2
  17. A. Sherstinsky, "Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network," Physica D: Nonlinear Phenomena, Vol.404, pp.132306, 2020. https://doi.org/10.1016/j.physd.2019.132306
  18. J. Zhao, et al., "Do rnn and lstm have long memory?," International Conference on Machine Learning, PMLR, 2020.
  19. Colah's Blog, Understanding LSTM Networks [Internet], Available from: http://colah.github.io/posts/2015-08-Understanding-LSTMs/(2015)
  20. 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
  21. F. A. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget: Continual prediction with LSTM," Neural Computation, Vol.12, No.10, pp.2451-2471, 2000. https://doi.org/10.1162/089976600300015015
  22. B. Lim and S. Zohren, "Time-series forecasting with deep learning: A survey," Philosophical Transactions of the Royal Society A, Vol.379, No.2194, pp.20200209, 2021. https://doi.org/10.1098/rsta.2020.0209
  23. R. Kumar, P. Kumar, and Y. Kumar, "Time series data prediction using iot and machine learning technique," Procedia Computer Science, Vol.167, pp.373-381, 2020. https://doi.org/10.1016/j.procs.2020.03.240
  24. I. Aijaz and P. Agarwal, "A study on time series forecasting using hybridization of time series models and neural networks," Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science) Vol.13, No.5, pp.827-832, 2020.