A Study on Traffic Prediction for the Backbone of Korea’s Research and Science Network Using Machine Learning

Authors

  • Chanjin Park 1) Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea 2) College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea
  • Wonhyuk Lee Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea https://orcid.org/0000-0002-1571-9638
  • Moon-Hyun Kim College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea
  • Ung-Mo Kim College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea
  • Taehong Kim Dept of Korean Medical Data, Korea Institute of Oriental Medicine, Daejeon, Korea
  • Seunghae Kim Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea

DOI:

https://doi.org/10.13052/jwe1540-9589.2152

Keywords:

Traffic Prediction, Machine Learning, SVR, LSTM, GRU, KREONET

Abstract

To fix network congestion resulting from the increase in high volume traffic in data-intensive science and the increase in internet traffic due to COVID-19, there has been a necessity of traffic engineering through traffic prediction. For this, there have been various attempts from a statistical method such as ARIMA to machine learning including LSTM and GRU. This study aimed to collect and learn KREOENT backbone and subscribers’ traffic volume through diverse machine learning techniques (e.g., SVR, LSTM, GRU, etc.) and predict maximum traffic on the following day.

Downloads

Download data is not yet available.

Author Biographies

Chanjin Park, 1) Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea 2) College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea

Chanjin Park received the master’s degree in computer engineering from Sungkyunkwan University in 2010, From 2012 to 2015, he has been a officer in Korea Military Academy, Seoul, Korea. And since 2015, he has been a engineer in Korea Institute of Science & Technology Information (KISTI), Daejon, Korea. His research area include network management, security, measurement and machine learning.

Wonhyuk Lee, Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea

Wonhyuk Lee received his Ph. D. degree in the department of computer engineering from Sungkyunkwan University, Korea, in 2010. Since 2003, he has been a senior engineer in Korea Institute of Science & Technology Information (KISTI), Daejon, Korea. His research interests include network management, security, measurement and next generation network.

Moon-Hyun Kim, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea

Moon-Hyun Kim received the B.S. degree in Electronic Engineering from Seoul National University in 1978, the M.S. degree in Electrical Engineering from Korea Advanced Institute of Science and Technology, Korea, in 1980, and the Ph.D. degree in Computer Engineering from the University of Southern California in 1988. From 1980 to 1983, he was a Research Engineer at the Daewoo Heavy Industries Co., Seoul. He joined College of Software, Sungkyunkwan University, Seoul, Korea in 1988, where he is currently a an emeritus professor. In 1995, he was a Visiting Scientist at the IBM Almaden Research Center, San Jose, California. In 1997, he was a Visiting Professor at the Signal Processing Laboratory of Princeton University, Princeton, New Jersey. His research interests include artificial intelligence, machine learning and pattern recognition.

Ung-Mo Kim, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea

Ung-Mo Kim received the bachelor’s degree in Mathematics from Sungkyunkwan University in 1981, the master’s degree in computer science from Old Dominion University in 1986, and the philosophy of doctorate degree in computer science from Northwestern University in 1990, respectively. He is currently working as a Full Professor at the College of Computing and Informatics, Sungkyunkwan University. His research areas include Database, Data Mining, Big Data.

Taehong Kim, Dept of Korean Medical Data, Korea Institute of Oriental Medicine, Daejeon, Korea

Taehong Kim received his M.S. and Ph.D. degrees from the Department of Applied Information Science at University of Science and Technology in 2010 and 2014, respectively. After graduation, he has conducted researches on Semantic Web, Big Data, and IoT in Korea Institute of Science and Technology Information until 2018. After that, he has expanded his research area to Korean medicine informatics in Korea Institute of Oriental Medicine. His research areas include person-generated health data, time-series data, and medical data analysis.

Seunghae Kim, Korea Research Environment Network Center, Korea Institute of Science and Technology Information, Daejeon, Korea

Seunghae Kim received the BS degees from the Hannam University, Korea and the MS and the PhD degrees from the Jeonbuk National University, Korea. He is currently a Network Engineer and Principal Reseacher at the Korea Institute Science and Technology Information. His research interests include Network architecture, Network security, Routing and Network Operation.

References

Huifang Feng, Yantai Shu, ‘Study on Network Traffic Prediction Techniques’, International Conference on Wireless Communications, Networking and Mobile Computing, pp. 1041–1044, 2005

Vinayakumar R, Soman KP, et al., ‘Applying Deep Learning Approaches for Network Traffic Prediction’, ICACCI, 2353–2358, 2017

Paulo Cortez, Miguel Rio, et al., ‘Internet Traffic Forecasting using Neural Networks’, International Joint Conference on Neural Networks, pp. 2635–2642, 2006

Nandini Krishnaswamy, Mariam Kiran, ‘Data-driven Learning to Predict WAN Network Traffic’, SNTA, pp. 11–18, 2020

Harris Drucker, Chirs J.C. Buges., et al., ‘Support Vector Regression Machines’, Advances in neural information processing systems 9, pp. 155–161, 1996

Chi-Jie Lu a, Tian-Shyug Lee, et al., ‘Financial time series forecasting using independent component analysis and support vector regression’, Decision Support Systems, pp. 115–125, 2009

Sepp Hochreiter, Jürgen Schmidhuber, ‘Long Short-term Memory’, Neural Computation, pp. 1735–1780, 1997

Dejun Chen, Congcong Xiong, et al., ‘Improved LSTM Based on Attention Mechanism for Short-term Traffic Flow Prediction’, 10th International Conference on Information Science and Technology, pp. 71–76, 2020

W. Esmail, T. Stockmanns, et al., ‘Machine Learning for Track Finding at PANDA’, Proceedings of the CTD/WIT, pp, 2019

Kyunghyun Cho, et al., ‘Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation’, EMNLP 2014, pp. 1724–1734, 2014

Rui Fu, Zuo Zhang, and Li Li, ‘Using LSTM and GRU Neural Network Methods for Traffic Flow Prediction’, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 324–328, 2016

Rob J. Hyndman, et al., ‘Another look at measures of forecast accuracy’, International Journal of Forecasting 22, pp. 697–688, 2006

The KREONET official website http://www.kreonet.net/kreonet/index.jsp

William Stallings, ‘SNMP and SNMPv2: The Infrastructure for Network Management’, IEEE Communications Magazine, pp. 37–43, 1998

Tobias Oetiker, ‘MRTG – The Multi Router Traffic Grapher’, 1998

D. Arthur, S. Vassilvitskii, ‘How Slow is the k-means Method?’ Proceedings of the 2006 Symposium on Computational Geometry, 2006

Yong-hwan Kim, Ki-Hyeon Kim, Dongkyun Kim, ‘Design and Implementation of Virtually Dedicated Network Service in SD-WAN Based Advanced Research & Educational (R&E) Network’, The Journal of Korean Institute of Communications and Information Sciences, pp. 2050–2064, 2017

Downloads

Published

2022-07-27

Issue

Section

SPECIAL ISSUE: Intelligent Edge Computing