Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction

Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.

[1]  Esther Jang,et al.  Cognitive all-optical fiber network architecture , 2017, 2017 19th International Conference on Transparent Optical Networks (ICTON).

[2]  Balachander Krishnamurthy,et al.  Sketch-based change detection: methods, evaluation, and applications , 2003, IMC '03.

[3]  Pedro Sousa,et al.  Multi‐scale Internet traffic forecasting using neural networks and time series methods , 2010, Expert Syst. J. Knowl. Eng..

[4]  Marco Ruffini,et al.  An Overview on Application of Machine Learning Techniques in Optical Networks , 2018, IEEE Communications Surveys & Tutorials.

[5]  Yuval Shavitt,et al.  Inferring the periodicity in large-scale Internet measurements , 2013, 2013 Proceedings IEEE INFOCOM.

[6]  G. Ellinas,et al.  Leveraging statistical machine learning to address failure localization in optical networks , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[7]  Raouf Boutaba,et al.  A comprehensive survey on machine learning for networking: evolution, applications and research opportunities , 2018, Journal of Internet Services and Applications.

[8]  Giang Nguyen,et al.  Deep Learning for Proactive Network Monitoring and Security Protection , 2020, IEEE Access.

[9]  Vittorio Curri,et al.  QoT Estimation for Light-path Provisioning in Un-Seen Optical Networks using Machine Learning , 2020, 2020 22nd International Conference on Transparent Optical Networks (ICTON).

[10]  Moshe Zukerman,et al.  Internet traffic modeling and future technology implications , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[11]  Roberto Proietti,et al.  Experimental demonstration of machine-learning-aided QoT estimation in multi-domain elastic optical networks with alien wavelengths , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[12]  D. Wolpert The Supervised Learning No-Free-Lunch Theorems , 2002 .

[13]  Masayuki Murata,et al.  Traffic prediction for dynamic traffic engineering , 2015, Comput. Networks.

[14]  Biswanath Mukherjee,et al.  Scheduling with machine-learning-based flow detection for packet-switched optical data center networks , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[15]  Danish Rafique,et al.  Machine learning for network automation: overview, architecture, and applications [Invited Tutorial] , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[16]  C. Vinchoff,et al.  Traffic Prediction in Optical Networks Using Graph Convolutional Generative Adversarial Networks , 2020, 2020 22nd International Conference on Transparent Optical Networks (ICTON).

[17]  Gianmarco De Francisci Morales,et al.  Big Data Stream Learning with SAMOA , 2014, 2014 IEEE International Conference on Data Mining Workshop.

[18]  Piotr Cholda,et al.  A time‐efficient shrinkage algorithm for the Fourier‐based prediction enabling proactive optimisation in software‐defined networks , 2020, Int. J. Commun. Syst..

[19]  Mohit Chamania,et al.  Artificial Intelligence (AI) Methods in Optical Networks: A Comprehensive Survey , 2018, Opt. Switch. Netw..

[20]  V. Alarcon-Aquino,et al.  Multiresolution FIR neural-network-based learning algorithm applied to network traffic prediction , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[21]  Michal Aibin,et al.  Traffic prediction based on machine learning for elastic optical networks , 2018, Opt. Switch. Netw..

[22]  Krzysztof Walkowiak,et al.  Dynamic routing in spectrally spatially flexible optical networks with back-to-back regeneration , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[23]  Vincent W. S. Chan Cognitive Optical Networks , 2018, 2018 IEEE International Conference on Communications (ICC).

[24]  Daniel Szostak,et al.  Short-Term Traffic Forecasting in Optical Network using Linear Discriminant Analysis Machine Learning Classifier , 2020, 2020 22nd International Conference on Transparent Optical Networks (ICTON).

[25]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..