DOI QR코드

DOI QR Code

A Study on the Quality Monitoring and Prediction of OTT Traffic in ISP

ISP의 OTT 트래픽 품질모니터링과 예측에 관한 연구

  • Nam, Chang-Sup (Department of Mechanical ICT Engineering, Hoseo University)
  • Received : 2021.03.21
  • Accepted : 2021.04.06
  • Published : 2021.04.30

Abstract

This paper used big data and artificial intelligence technology to predict the rapidly increasing internet traffic. There have been various studies on traffic prediction in the past, but they have not been able to reflect the increasing factors that induce huge Internet traffic such as smartphones and streaming in recent years. In addition, event-like factors such as the release of large-capacity popular games or the provision of new contents by OTT (Over the Top) operators are more difficult to predict in advance. Due to these characteristics, it was impossible for an ISP (Internet Service Provider) to reflect real-time service quality management or traffic forecasts in the network business environment with the existing method. Therefore, in this study, in order to solve this problem, an Internet traffic collection system was constructed that searches, discriminates and collects traffic data in real time, separate from the existing NMS. Through this, the flexibility and elasticity to automatically register the data of the collection target are secured, and real-time network quality monitoring is possible. In addition, a large amount of traffic data collected from the system was analyzed by machine learning (AI) to predict future traffic of OTT operators. Through this, more scientific and systematic prediction was possible, and in addition, it was possible to optimize the interworking between ISP operators and to secure the quality of large-scale OTT services.

본 논문은 급증하는 인터넷 트래픽예측을 위해 빅데이터와 인공지능기술을 이용하였다. 기존에 트래픽 예측에 관해 다양한 연구가 있었지만 최근 스마트폰이나 스트리밍 등 거대한 인터넷 트래픽을 유발하는 증가 요소를 반영하지는 못했다. 더불어 대용량 인기 게임 출시나 OTT(Over the Top)사업자의 신규 컨텐츠 제공과 같은 이벤트성 요소는 사전 예측이 더욱 어렵다. 이러한 특성으로 기존 방법으로는 ISP(Internet Service Provider)가 실시간적 서비스 품질관리나 트래픽 예측치를 네트워크 사업환경에 반영하기가 불가능하였다. 따라서 본 연구에서는 이러한 문제점을 해결하고자 기존 NMS와는 별개로 트래픽 데이터를 실시간적으로 탐색, 판별하여 수집하는 인터넷 트래픽 수집시스템을 구축하였다. 이를 통해 수집대상의 데이터를 자동등록할 수 있는 유연성과 탄력성을 확보하였으며 실시간 네트워크 품질모니터링을 가능하게 하였다. 또한 시스템에서 수집된 대량의 트래픽 데이터를 머신러닝(AI)으로 분석하여 OTT 사업자의 미래 트래픽을 예측하였다. 이를 통해 보다 과학적이고 체계적인 예측이 가능해졌으며 더불어 ISP 사업자 간의 연동 최적화와 대형 OTT 서비스의 품질확보가 가능할 수 있게 되었다.

Keywords

References

  1. Tikunov, D. and Nishimura, T. "Traffic Prediction for Mobile Network using Holt-Winter's Exponential Smoothing", Telecommunications and Computer Networks, 15th International Conference, 1-5. 2007
  2. H. NIE et al. "Hybrid of ARIMA and SVMs for Short-Term Load Forecasting," International Conference on Future Energy, Environment, and Materials, pp.1455-1460, 2012
  3. Shu, Y., Yu, M., Yang, O., Liu, J. and Feng, H. "Wireless traffic modeling and prediction using seasonal ARIMA models", IEICE-transactions on Communications, 10, 3992-3999. 2005
  4. L.R. Medsker, L.C. Jain ,"Recurrent Neural Network; Design and Applications",p.12-14, 2001
  5. Luis G. B. R., Manuel P. C., Miguel, D. C. and Maria D. C. P. J., "An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings," energies, 9(9), p.684, Aug. 2016. https://doi.org/10.3390/en9090684
  6. L.R. Medsker, L.C. Jain ,"Recurrent Neural Network; Design and Applications",p.12-14, 2001
  7. DH Kim, MW Kim, BJ Lee, KT Kim, HY Youn, "Data Flow Prediction Scheme using ARIMA Model",Proceedings of the Korean Society of Computer Information Conference 26(2), 2018.7, 141-142
  8. JKLee, IP Cho, SY Lee"A study on data collection environment and analysis using virtual server hosting of Azure cloud platform, Proceedings of the Korean Society of Computer Information Conference , 2020.7, 329-330
  9. MH Ha, HG Sona, S. Kim,"A Study on Performance Analysis of ShortTerm Internet Traffic Forecasting Models",Proceedings of KICS. 2012, 19(3B), 415-422
  10. SJ. Jung, DJ Kim, YH Kwon "A Fitness Verification of time Series Models for Network Traffic Predictions", Proceedings of KICS. 2004 29(2B), 217-227
  11. SH Ji, Huru Hasanova, KS Shim, MS Kim. "Prediction of Traffic Usage Using Machine Learning Algorithm For Efficient Network Management",Proceedings of Symposium of KICS, 2018.1, 824-825
  12. Jin Sheng, MS Seok, GY Kim, "Internet Traffic Prediction By Neural Networks", Proceedings of Symposium of KICS , 019.6, 211-213
  13. JS Won, SW Kim, "VNF traffic Prediction Using Recurrent Neural Network", Proceedings of Symposium of The Institute of Electronics and Information Engineers 2018.6, 351-353