Classificação de Tráfego para Gerenciamento de Largura de Banda em Redes Definidas por Software
Abstract
Applications have different requirements in terms of bandwidth and delay to deliver the expected quality of service. For this and other reasons, new paradigms have emerged, such as software-defined networks, which allow the development of new applications for dynamic programming of routing devices in the network through a device called controller. In this work, five machine learning models for classifying network traffic are tested, which when implemented in the controller make it possible to discover the types of applications and their quality of service requirements. The obtained results demonstrate that the Random Forest model has an excellent performance in the classification of network traffic using few packets and achieves very high accuracy margins. On the other hand, it was noted that machine learning models based on streaming data are very sensitive to the database and the amount of packets used in the classification.
References
Alkazaz, A. and Saado Kharouki, M. (2020). Evaluation of adaptive random forest algorithm for classification of evolving data stream.
Amaral, P., Dinis, J., Pinto, P., Bernardo, L., Tavares, J., and Mamede, H. (2016a). Machine learning in software defined networks: Data collection and traffic classification. In 2016 IEEE 24th International Conference on Network Protocols, pages 1–5.
Amaral, P., Dinis, J., Pinto, P., Bernardo, L., Tavares, J., and Mamede, H. S. (2016b). Machine learning in software defined networks: Data collection and traffic classification. In 2016 IEEE 24th International conference on network protocols (ICNP), pages 1–5. IEEE.
Biondi, P. (2023). Welcome to scapy’s documentation! [link].
Gandhi, R. (2018). Support vector machine — introduction to machine learning algorithms. [link].
Google (2023). System requirements and supported devices for youtube. [link].
Huawei (2022). Overview of bandwidth managementt. [link].
ITU (2001). End-user multimedia QoS categories. International Telecommunication Union (ITU).
Karakus, M. and Durresi, A. (2017). Quality of service (qos) in software defined networking (sdn): A survey. Journal of Network and Computer Applications, 80:200 – 218.
Microsoft (2023). How much bandwidth does skype need? [link].
Mocelin Júnior, N. J. and Fiorese, A. (2023). Flowprisdn: A framework for bandwidth management for prioritary data flows applied to a smart city scenario. In International Conference on Advanced Information Networking and Applications, pages 346–357. Springer.
Navlani, A. (2023). Decision tree classification in python tutorial. [link].
Rabello, E. B. (2017). Cross validation: Avaliando seu modelo de machine learning. [link].
Raikar, M. M., Meena, S., Mulla, M. M., Shetti, N. S., and Karanandi, M. (2020). Data traffic classification in software defined networks (sdn) using supervised-learning. Procedia Computer Science, 171:2750–2759.
UNB (2016). Vpn-nonvpn dataset (iscxvpn2016). [link].
Verma, Y. (2021). A beginner’s guide to hoeffding tree with python implementation. [link].
Yan Chen, Toni Farley, N. Y. (2004). Qos requirements of network applications on the internet. Systems Management, 4.
Zander, S., Nguyen, T., and Armitage, G. (2012). Sub-flow packet sampling for scalable ml classification of interactive traffic. In 37th Annual IEEE Conference on Local Computer Networks, pages 68–75.
Zhou, D., Yan, Z., Fu, Y., and Yao, Z. (2018). A survey on network data collection. Journal of Network and Computer Applications, 116:9–23.
Zivkovic, S. (2022). Machine learning – introduction to random forest. [link].
