Novel Machine Learning (ML) Algorithms to Classify IPv6 Network Traffic in Resource-Limited Systems

Abstract

Providing machine learning (ML) based security in heterogeneous IoT networks including resource-constrained devices is a challenge because of the fact that conventional ML algorithms require heavy computations. Therefore, in this paper, lightweight ProtoNN, CMSIS-NN, and Bonsai tree ML algorithms were evaluated by using performance metrics such as testing accuracy, precision, F1 score and recall to test their classification ability on the IPv6 network dataset generated on resource-scarce embedded devices. The Bonsai tree algorithm provided the best performance results in all metrics (98.8 in accuracy, 98.9% in F1 score, 99.2% in precision, and 98.8% in recall) compared to the ProtoNN, and CMSIS-NN algorithms.