Benchmarking da eficiência dos algoritmos supervisionados de ML na classificação de tráfego NFV
DOI:
https://doi.org/10.18046/syt.v15i42.2539Palavras-chave:
Tráfego IP, NFV, Aprendizado de máquinas, algoritmos supervisionados.Resumo
A implementação de NFV permite melhorar a flexibilidade, a eficiência e a capacidade de gerenciamento das redes aproveitando a virtualização e as tecnologias da computação em nuvem para implantar redes informáticas. A implementação de gerenciamento autônomo e algoritmos supervisionados de Aprendizado de Máquinas (Machine Learning - ML) tornam-se uma estratégia chave para gerenciar esse tráfego oculto. Neste trabalho, nosso foco é a análise das características do tráfego em redes baseadas em NFV, ao mesmo tempo em que realizamos uma avaliação comparativa do comportamento dos algoritmos supervisionados de ML, isto é, J48, Naïve Bayes e Bayes Net na classificação de tráfego IP em relação à sua eficiência; considerando que essa eficiência está relacionada ao equilíbrio entre o tempo de resposta e precisão. Foram utilizados dois cenários de teste (um SDN baseado em NFV e um LTE EPC baseado em NFV). Os resultados da avaliação comparativa revelam que os algoritmos Naïve Bayes e Bayes Net têm o melhor desempenho na classificação do tráfego. Em particular, seu desempenho corrobora um bom equilíbrio entre a precisão e o tempo de resposta, com valores de precisão superiores a 80% e 96%, respectivamente, para tempos inferiores a 1,5 segundos.
Referências
Agoulmine, N. (2010). Autonomic network management principles: From concepts to applications. Amsterdam, The Netherlands: Elsevier.
Botta, A., Dainotti, A., & Pescapé, A. (2012). A tool for the generation of realistic network workload for emerging networking scenarios. Computer Networks, 56(15), 3531-3547.
Bujlow, T., Riaz, T., & Pedersen, J. M. (2012, January). A method for classification of network traffic based on C5. 0 Machine Learning Algorithm. In Computing, Networking and Communications (ICNC), 2012 International Conference on (pp. 237-241). IEEE.
Carela-Español, V., Barlet-Ros, P., Mula-Valls, O., & Sole-Pareta, J. (2015). An autonomic traffic classification system for network operation and management. Journal of Network and Systems Management, 23(3), 401-419.
Chapelle, O., Haffner, P., & Vapnik, V. (1999). Support vector machines for histogram-based image classification. IEEE transactions on Neural Networks, 10(5), 1055-1064.
Chi, P. W., Huang, Y. C., & Lei, C. L. (2015, June). Efficient NFV deployment in data center networks. In Communications (ICC), 2015 IEEE International Conference on (pp. 5290-5295). IEEE.
Chishti, H. R. (2013). A traffic classification method using machine learning algorithm [thesis]. Luton, UK: University of Bedfordshire.
Choudhury, S., & Bhowal, A. (2015). Comparative analysis of machine learning algorithms along with classifiers for network intrusion detection. In Smart Technologies and Management for Computing, Communication,
Controls, Energy and Materials (ICSTM), 2015 International Conference on (pp. 89-95). IEEE.
Cotroneo, D., De Simone, L., Iannillo, A. K., Lanzaro, A., Natella, R., Fan, J., & Ping, W. (2014). Network function virtualization: Challenges and directions for reliability assurance. In Software Reliability Engineering Workshops (ISSREW), 2014 IEEE International Symposium on (pp. 37-42). IEEE
Firoozjaei, M. D., Jeong, J. P., Ko, H., & Kim, H. (2017). Security challenges with network functions virtualization. Future Generation Computer Systems, 67, 315-324.
Frank, E. (2010). Weka-A machine learning workbench for data mining. In Data mining and knowledge discovery handbook (pp. 1269-1277). Boston, MA: Springer.
Gray, K. (2016). Network function virtualization. Boston, MA: Morgan Kaufmann.
He, L., Xu, C., & Luo, Y. (2016). VTC: Machine learning based traffic classification as a virtual network function. In Proceedings of the 2016 ACM International Workshop on Security in Software Defined Networks & Network Function Virtualization (pp. 53-56). New York, NY: ACM.
iPerf. (2017). iPerf - The ultimate speed test tool for TCP, UDP and SCTP. Retrieved from https://iperf.fr/
Ixia. (2016). Network function virtualization (nfv): 5 major risks. Retrieved from https://www.ixiacom.com/resources/network-function-virtualization-nfv-5-major-risks
Kephart, J. O. & Chess D. M. (2003). The vision of autonomic computing. Computer, 36(1), 41-50.
Kumar, J., Satapaphy, P., Sadagopan, N., & Vutukuru, M. (2016). Virtualized evolved eacket core for LTE networks. Retrieved from: https://github.com/networkedsystemsIITB/NFV_LTE_EPC
Li, W., Canini, M., Moore, A. W., & Bolla, R. (2009). Efficient application identification and the temporal and spatial stability of classification schema. Computer Networks, 53(6), 790-809.
Mearns, H., & Leaney, J. (2013, April). The use of autonomic management in multi-provider telecommunication services. In Engineering of Computer Based Systems (ECBS), 2013 20th IEEE International Conference and Workshops on the (pp. 129-138). IEEE.
Ma, W., Medina, C., & Pan, D. (2015, December). Traffic-aware placement of NFV middle boxes. In Global Communications Conference (GLOBECOM), 2015 IEEE (pp. 1-6). IEEE.
Maglogiannis, I. (Ed.) (2007). Emerging artificial intelligence applications in computer engineering: real word ai systems with applications in ehealth, hci, information retrieval and pervasive technologies. Amsterdam, The Netherlands: IOS.
Mininet: An instant virtual network on your laptop (or other PC). (2017). Retrieved from http://mininet.org
Muralidharan, V., & Sugumaran, V. (2012). A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing, 12(8), 2023-2029.
Novakovic, J. (2016). Toward optimal feature selec-tion using ranking methods and classi-fication algorithms. Yugoslav Journal of Operations Research, 21(1), 119-135.
OVS - Openv vSwitch. (n.d.). Retrieved from http://openvswitch.org/
Qin, D., Yang, J., Wang, J., & Zhang, B. (2011, September). IP traffic classification based on machine learning. In Communication Technology (ICCT), 2011 IEEE 13th International Conference on (pp. 882-886). IEEE.
RYU SDN framework. (2017). Retrieved from http://osrg.github.io/ryu/
Shafiq, M., Yu, X., Laghari, A. A., Yao, L., Karn, N. K., & Abdessamia, F. (2016a). Network traffic classification techniques and comparative analysis using machine learning algorithms. In Computer and Communications (ICCC), 2016 2nd IEEE International Conference on (pp. 2451-2455). IEEE.
Shafiq, M., Yu, X., Laghari, A., Yao, L., Karn, N., Abdesssamia, F., & Salahuddin, S. (2016b). We chat text and picture messages service flow traffic classification using machine learning Technique. In IEEE HPCC/SmartCity/DSS (pp. 58-62).
Shankara, U. (2007). Patent No. 20070220217. Bengalooru, IN.
Singh, K., Agrawal, S., & Sohi, B. S. (2013). A near real-time IP traffic classification using machine learning. International Journal of Intelligent Systems and Applications, 5(3), 83.
Solomon, B., Ionescu, D., Litoiu, M., & Iszlai, G. (2010, May). Designing autonomic management systems for cloud computing. In Computational Cybernetics and Technical Informatics (ICCC-CONTI), 2010 International Joint Conference on (pp. 631-636). IEEE.
Sugumaran, V. M. (2012). A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing, 12(8), 2023 - 2029.
Tsagkaris, K., Logothetis, M., Foteinos, V., Poulios, G., Michaloliakos, M., & Demestichas, P. (2015). Customizable autonomic network management: integrating autonomic network management and software-defined networking. IEEE Vehicular Technology Magazine, 10(1), 61-68.
Valdes, A., Macwan, R., & Backes, M. (2016). anomaly detection in electrical substation circuits via unsupervised machine learning. In Information Reuse and Integration (IRI), 2016 IEEE 17th International Conference on (pp. 500-505). IEEE.
VMware. (2017). Retrieved from https://www.vmware.com/
Weingärtner, R., Bräscher, G. B., & Westphall, C. B. (2016, June). A distributed autonomic management framework for cloud computing orchestration. In Services (SERVICES), 2016 IEEE World Congress on (pp. 9-17). IEEE.
Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Amsterdam, The Netherlands: Elsevier.
Zander, S., & Armitage, G. (2011, October). Practical machine learning based multimedia traffic classification for distributed QoS management. In Local Computer Networks (LCN), 2011 IEEE 36th Conference on (pp. 399-406). IEEE.
Zhu, J. (2014). Quantitative models for performance evaluation and benchmarking: data envelopment analysis with spreadsheets. New York, NY: Springer.
Botta, A., Dainotti, A., & Pescapé, A. (2012). A tool for the generation of realistic network workload for emerging networking scenarios. Computer Networks, 56(15), 3531-3547.
Bujlow, T., Riaz, T., & Pedersen, J. M. (2012, January). A method for classification of network traffic based on C5. 0 Machine Learning Algorithm. In Computing, Networking and Communications (ICNC), 2012 International Conference on (pp. 237-241). IEEE.
Carela-Español, V., Barlet-Ros, P., Mula-Valls, O., & Sole-Pareta, J. (2015). An autonomic traffic classification system for network operation and management. Journal of Network and Systems Management, 23(3), 401-419.
Chapelle, O., Haffner, P., & Vapnik, V. (1999). Support vector machines for histogram-based image classification. IEEE transactions on Neural Networks, 10(5), 1055-1064.
Chi, P. W., Huang, Y. C., & Lei, C. L. (2015, June). Efficient NFV deployment in data center networks. In Communications (ICC), 2015 IEEE International Conference on (pp. 5290-5295). IEEE.
Chishti, H. R. (2013). A traffic classification method using machine learning algorithm [thesis]. Luton, UK: University of Bedfordshire.
Choudhury, S., & Bhowal, A. (2015). Comparative analysis of machine learning algorithms along with classifiers for network intrusion detection. In Smart Technologies and Management for Computing, Communication,
Controls, Energy and Materials (ICSTM), 2015 International Conference on (pp. 89-95). IEEE.
Cotroneo, D., De Simone, L., Iannillo, A. K., Lanzaro, A., Natella, R., Fan, J., & Ping, W. (2014). Network function virtualization: Challenges and directions for reliability assurance. In Software Reliability Engineering Workshops (ISSREW), 2014 IEEE International Symposium on (pp. 37-42). IEEE
Firoozjaei, M. D., Jeong, J. P., Ko, H., & Kim, H. (2017). Security challenges with network functions virtualization. Future Generation Computer Systems, 67, 315-324.
Frank, E. (2010). Weka-A machine learning workbench for data mining. In Data mining and knowledge discovery handbook (pp. 1269-1277). Boston, MA: Springer.
Gray, K. (2016). Network function virtualization. Boston, MA: Morgan Kaufmann.
He, L., Xu, C., & Luo, Y. (2016). VTC: Machine learning based traffic classification as a virtual network function. In Proceedings of the 2016 ACM International Workshop on Security in Software Defined Networks & Network Function Virtualization (pp. 53-56). New York, NY: ACM.
iPerf. (2017). iPerf - The ultimate speed test tool for TCP, UDP and SCTP. Retrieved from https://iperf.fr/
Ixia. (2016). Network function virtualization (nfv): 5 major risks. Retrieved from https://www.ixiacom.com/resources/network-function-virtualization-nfv-5-major-risks
Kephart, J. O. & Chess D. M. (2003). The vision of autonomic computing. Computer, 36(1), 41-50.
Kumar, J., Satapaphy, P., Sadagopan, N., & Vutukuru, M. (2016). Virtualized evolved eacket core for LTE networks. Retrieved from: https://github.com/networkedsystemsIITB/NFV_LTE_EPC
Li, W., Canini, M., Moore, A. W., & Bolla, R. (2009). Efficient application identification and the temporal and spatial stability of classification schema. Computer Networks, 53(6), 790-809.
Mearns, H., & Leaney, J. (2013, April). The use of autonomic management in multi-provider telecommunication services. In Engineering of Computer Based Systems (ECBS), 2013 20th IEEE International Conference and Workshops on the (pp. 129-138). IEEE.
Ma, W., Medina, C., & Pan, D. (2015, December). Traffic-aware placement of NFV middle boxes. In Global Communications Conference (GLOBECOM), 2015 IEEE (pp. 1-6). IEEE.
Maglogiannis, I. (Ed.) (2007). Emerging artificial intelligence applications in computer engineering: real word ai systems with applications in ehealth, hci, information retrieval and pervasive technologies. Amsterdam, The Netherlands: IOS.
Mininet: An instant virtual network on your laptop (or other PC). (2017). Retrieved from http://mininet.org
Muralidharan, V., & Sugumaran, V. (2012). A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing, 12(8), 2023-2029.
Novakovic, J. (2016). Toward optimal feature selec-tion using ranking methods and classi-fication algorithms. Yugoslav Journal of Operations Research, 21(1), 119-135.
OVS - Openv vSwitch. (n.d.). Retrieved from http://openvswitch.org/
Qin, D., Yang, J., Wang, J., & Zhang, B. (2011, September). IP traffic classification based on machine learning. In Communication Technology (ICCT), 2011 IEEE 13th International Conference on (pp. 882-886). IEEE.
RYU SDN framework. (2017). Retrieved from http://osrg.github.io/ryu/
Shafiq, M., Yu, X., Laghari, A. A., Yao, L., Karn, N. K., & Abdessamia, F. (2016a). Network traffic classification techniques and comparative analysis using machine learning algorithms. In Computer and Communications (ICCC), 2016 2nd IEEE International Conference on (pp. 2451-2455). IEEE.
Shafiq, M., Yu, X., Laghari, A., Yao, L., Karn, N., Abdesssamia, F., & Salahuddin, S. (2016b). We chat text and picture messages service flow traffic classification using machine learning Technique. In IEEE HPCC/SmartCity/DSS (pp. 58-62).
Shankara, U. (2007). Patent No. 20070220217. Bengalooru, IN.
Singh, K., Agrawal, S., & Sohi, B. S. (2013). A near real-time IP traffic classification using machine learning. International Journal of Intelligent Systems and Applications, 5(3), 83.
Solomon, B., Ionescu, D., Litoiu, M., & Iszlai, G. (2010, May). Designing autonomic management systems for cloud computing. In Computational Cybernetics and Technical Informatics (ICCC-CONTI), 2010 International Joint Conference on (pp. 631-636). IEEE.
Sugumaran, V. M. (2012). A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis. Applied Soft Computing, 12(8), 2023 - 2029.
Tsagkaris, K., Logothetis, M., Foteinos, V., Poulios, G., Michaloliakos, M., & Demestichas, P. (2015). Customizable autonomic network management: integrating autonomic network management and software-defined networking. IEEE Vehicular Technology Magazine, 10(1), 61-68.
Valdes, A., Macwan, R., & Backes, M. (2016). anomaly detection in electrical substation circuits via unsupervised machine learning. In Information Reuse and Integration (IRI), 2016 IEEE 17th International Conference on (pp. 500-505). IEEE.
VMware. (2017). Retrieved from https://www.vmware.com/
Weingärtner, R., Bräscher, G. B., & Westphall, C. B. (2016, June). A distributed autonomic management framework for cloud computing orchestration. In Services (SERVICES), 2016 IEEE World Congress on (pp. 9-17). IEEE.
Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Amsterdam, The Netherlands: Elsevier.
Zander, S., & Armitage, G. (2011, October). Practical machine learning based multimedia traffic classification for distributed QoS management. In Local Computer Networks (LCN), 2011 IEEE 36th Conference on (pp. 399-406). IEEE.
Zhu, J. (2014). Quantitative models for performance evaluation and benchmarking: data envelopment analysis with spreadsheets. New York, NY: Springer.
Downloads
Publicado
2017-10-19
Edição
Seção
Original Research
Licença
Esta publicação está licenciada sob os termos da licença CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/deed.pt_BR).
