Descobrindo perfis de tráfego de usuários: uma abordagem não supervisionada
Resumo
As redes domésticas estão cada vez mais complexas. Portanto, é essencial a elaboração de estratégias inovadoras para caracterizar essa nova demanda. Neste trabalho usamos técnicas não supervisionadas de aprendizado de máquina com o objetivo de entender o perfil de tráfego dos usuários. Em parceria com um ISP, coletamos o tráfego de download e upload de mais de 2.000 roteadores domésticos. Usamos uma técnica de decomposição de tensores (PARAFAC) para extrair fatores relevantes de uso da rede e um algoritmo de clusterização para agrupar usuários com padrões de tráfego diário similares. Para caracterizar o comportamento dos usuários em períodos maiores que um dia, usamos a informação dos clusters e um modelo de Markov oculto.
Palavras-chave:
Gerenciamento de Redes, Aprendizado de Máquina, Monitoramento, Análise de Dados
Referências
Bro, R. (1997). Parafac. tutorial and applications. Chemometrics and intelligent laboratory systems, 38(2):149–171.
Crovella, M. and Krishnamurthy, B. (2006). Internet measurement: infrastructure, traffic and applications. John Wiley & Sons, Inc.
Fumo, A., Fiore, M., and Stanica, R. (2017). Joint spatial and temporal classification of mobile traffic demands. In INFOCOM, pages 1–9. IEEE.
Harshman, R. A. (1984). ”how can i know if it’s real?”a catalogue of diagnostics for use with three-mode factor analysis and multidimensional scaling. Research methods for multimode data analysis, pages 566–591.
Harshman, R. A. and Lundy, M. E. (1984). The parafac model for three-way factor analysis and multidimensional scaling. Research methods for multimode data analysis, 46:122–215.
Kaiser, H. F. (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23(3):187–200.
Kim, J., Hwang, J., and Kim, K. (2016). High-performance internet traffic classification using a markov model and kullback-leibler divergence. Mobile Information Systems, 2016.
Kroonenberg, P. M. (1983). Three-mode principal component analysis: Theory and applications, volume 2. DSWO press.
Kruskal, J. (1983). Multilinear methods. In Proc. Symp. Appl. Math, volume 28, page 75.
Legendre, P. and Legendre, L. (2012). Numerical ecology. 3rd. Elsevier.
Lorenzo-Seva, U. and Ten Berge, J. M. (2006). Tucker’s congruence coefficient as a meaningful index of factor similarity. Methodology, 2(2):57–64.
Morichetta, A. and Mellia, M. (2018). Lenta: Longitudinal exploration for network traffic analysis. In ITC.
Nguyen, T. T. and Armitage, G. (2008). A survey of techniques for internet traffic classification using machine learning. IEEE Communications Surveys & Tutorials, 10(4):56– 76.
Rabanser, S., Shchur, O., and G¨unnemann, S. (2017). Introduction to tensor decompositions and their applications in machine learning. arXiv preprint arXiv:1711.10781.
Rabiner, L. R. (1989). A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257–286.
Sidiropoulos, N. D., De Lathauwer, L., Fu, X., Huang, K., Papalexakis, E. E., and Faloutsos, C. (2017). Tensor decomposition for signal processing and machine learning. IEEE Transactions on Signal Processing, 65(13):3551–3582.
Smilde, A., Bro, R., and Geladi, P. (2005). Multi-way analysis: applications in the chemical sciences. John Wiley & Sons.
Soysal, M. and Schmidt, E. G. (2010). Machine learning algorithms for accurate flowbased network traffic classification: Evaluation and comparison. Performance Evaluation, 67(6):451–467.
Stedmon, C. A. and Bro, R. (2008). Characterizing dissolved organic matter fluorescence with parallel factor analysis: a tutorial. Limnology and Oceanography: Methods, 6(11):572–579.
Trevisan, M., Giordano, D., Drago, I., Mellia, M., and Munafo, M. (2018). Five years at the edge: Watching internet from the isp network. In Proceedings of the 14th International
Conference on Emerging Networking EXperiments and Technologies, CoNEXT ’18, pages 1–12.
Wright, C., Monrose, F., and Masson, G. M. (2004). Hmm profiles for network traffic classification. In Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security, pages 9–15. ACM.
Crovella, M. and Krishnamurthy, B. (2006). Internet measurement: infrastructure, traffic and applications. John Wiley & Sons, Inc.
Fumo, A., Fiore, M., and Stanica, R. (2017). Joint spatial and temporal classification of mobile traffic demands. In INFOCOM, pages 1–9. IEEE.
Harshman, R. A. (1984). ”how can i know if it’s real?”a catalogue of diagnostics for use with three-mode factor analysis and multidimensional scaling. Research methods for multimode data analysis, pages 566–591.
Harshman, R. A. and Lundy, M. E. (1984). The parafac model for three-way factor analysis and multidimensional scaling. Research methods for multimode data analysis, 46:122–215.
Kaiser, H. F. (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23(3):187–200.
Kim, J., Hwang, J., and Kim, K. (2016). High-performance internet traffic classification using a markov model and kullback-leibler divergence. Mobile Information Systems, 2016.
Kroonenberg, P. M. (1983). Three-mode principal component analysis: Theory and applications, volume 2. DSWO press.
Kruskal, J. (1983). Multilinear methods. In Proc. Symp. Appl. Math, volume 28, page 75.
Legendre, P. and Legendre, L. (2012). Numerical ecology. 3rd. Elsevier.
Lorenzo-Seva, U. and Ten Berge, J. M. (2006). Tucker’s congruence coefficient as a meaningful index of factor similarity. Methodology, 2(2):57–64.
Morichetta, A. and Mellia, M. (2018). Lenta: Longitudinal exploration for network traffic analysis. In ITC.
Nguyen, T. T. and Armitage, G. (2008). A survey of techniques for internet traffic classification using machine learning. IEEE Communications Surveys & Tutorials, 10(4):56– 76.
Rabanser, S., Shchur, O., and G¨unnemann, S. (2017). Introduction to tensor decompositions and their applications in machine learning. arXiv preprint arXiv:1711.10781.
Rabiner, L. R. (1989). A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257–286.
Sidiropoulos, N. D., De Lathauwer, L., Fu, X., Huang, K., Papalexakis, E. E., and Faloutsos, C. (2017). Tensor decomposition for signal processing and machine learning. IEEE Transactions on Signal Processing, 65(13):3551–3582.
Smilde, A., Bro, R., and Geladi, P. (2005). Multi-way analysis: applications in the chemical sciences. John Wiley & Sons.
Soysal, M. and Schmidt, E. G. (2010). Machine learning algorithms for accurate flowbased network traffic classification: Evaluation and comparison. Performance Evaluation, 67(6):451–467.
Stedmon, C. A. and Bro, R. (2008). Characterizing dissolved organic matter fluorescence with parallel factor analysis: a tutorial. Limnology and Oceanography: Methods, 6(11):572–579.
Trevisan, M., Giordano, D., Drago, I., Mellia, M., and Munafo, M. (2018). Five years at the edge: Watching internet from the isp network. In Proceedings of the 14th International
Conference on Emerging Networking EXperiments and Technologies, CoNEXT ’18, pages 1–12.
Wright, C., Monrose, F., and Masson, G. M. (2004). Hmm profiles for network traffic classification. In Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security, pages 9–15. ACM.
Publicado
06/05/2019
Como Citar
STREIT, Ananda G.; LEÃO, Rosa M. M.; DE SOUZA E SILVA, Edmundo; MENASCHÉ, Daniel S..
Descobrindo perfis de tráfego de usuários: uma abordagem não supervisionada. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 37. , 2019, Gramado.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 169-182.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2019.7358.
