An efficient approach for device identification and traffic classification in IoT ecosystems

Abstract

Internet of Things arises as a computational paradigm that promotes the interconnection of objects to the Internet and enables interaction, operational efficiency, and communication. With the increasing inclusion in the network of intelligent objects that have characteristics such as diversity, heterogeneity, mobility and low computational power, it is fundamental to develop mechanisms that allow management and control. In addition, it is important to identify whether the assets are working properly or have anomalies. Traffic classification techniques are important to aid in network analysis and to handle many other key aspects such as security, management, access control, provisioning, and resource allocation. In order to promote the identification of network devices, especially IoT, this article presents a technique that uses Random Forest, a supervised automatic learning algorithm, together with the inspection of the contents of the packages for this purpose. Also, we use the same algorithm to perform the classification of network traffic. In the end, the identification of the devices showed an accuracy of approximately 99%.