Proposed Data Warehouse Architecture for SDN Analysis and Machine Learning Applications

  • Fernando Moro IFC
  • Rodrigo Nogueira IFC
  • Alexandre Amaral IFC
  • Ana Amaral IFC

Abstract


This paper presents the proposal of a Data Warehouse architecture that has as its data source and object of study IP streams and SDN attacks. The purpose of the proposal is to provide a consistent and clean data set for machine learning applications and any application wishing to consume data from this feature. To achieve the proposed objectives a multidimensional database was developed, which is fed by an ETL step based on the collection of network streams. Among the results obtained is the architecture itself, in which a data set can be explored through OLAP queries by machine learning applications.

Keywords: Data Warehouse, Machine Learning, SDN Attack

References

Amaral, A. A. (2015). Computação autonômica aplicada ao diagnóstico e solução de anomalias de redes de computadores. Universidade Estadual de Campinas (UNICAMP).

Costa, L. R. (2013). OpenFlow e o Paradigma de Redes Definidas por Software. Universidade de Brasília.

Huang, N.-F., Li, C.-C., Li, C.-H., et al. (2017). Application identification system for SDN QoS based on machine learning and DNS responses. In 2017 19th Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE.

Kimball, R. and Ross, M. (2011). The data warehouse toolkit: the complete guide todimensional modeling. 2nd revised ed. Canada: John Wiley and Sons, Inc.

Lopez, M. A., Lobato, A. G. P., Mattos, D. M. F. and Alvarenga, I. D. (2017). Um Algoritmo Não Supervisionado e Rápido para Seleção de Características em Classificação de Tráfego. In XXXV Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. Sociedade Brasileira de Computação (SBC).

Losarwar, V. and Joshi, D. M. (2012). Data Preprocessing in Web Usage Mining. In International Conference on Artificial Intelligence and Embedded Systems(ICAIES’2012).

Mansmann, S., Ur Rehman, N., Weiler, A. and Scholl, M. H. (2014). Discovering OLAP dimensions in semi-structured data. Information Systems, v. 44, p. 120–133.

Moro, F. L., Amaral, A., Amaral, A. P. and Nogueira, R. (nov 2017). Detecção e autorreparo de anomalias em redes definidas por software. In XVII Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais. Sociedade Brasileira de Computação (SBC).

Nogueira, R. (2017). Newsminer: um sistema de data warehouse baseado em textos de notícias. Universidade Federal de São Carlos (UFSCar).
Published
2019-04-10
MORO, Fernando; NOGUEIRA, Rodrigo; AMARAL, Alexandre; AMARAL, Ana. Proposed Data Warehouse Architecture for SDN Analysis and Machine Learning Applications. In: REGIONAL DATABASE SCHOOL (ERBD), 15. , 2019, Chapecó. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 121-130. ISSN 2595-413X. DOI: https://doi.org/10.5753/erbd.2019.8485.