Community Network Traffic Classification Using Two-Dimensional Convolutional Neural Networks

Network traffic classification plays an important role in quality of service engineering. In recent years, it has become apparent that deep learning techniques are effective for this classification task, especially since classical approaches struggle to deal with encrypted traffic. However, deep learning models often tend to be computationally expensive, which weakens their suitability in low-resource community networks. This paper explores the computational efficiency and accuracy of two-dimensional convolutional neural networks (2D-CNNs) deep learning models for packet-based classification of traffic in a community network. We find that 2D-CNNs models attain higher out-of-sample accuracy than traditional support vector machines classifiers and the simpler multi-layer perceptron neural networks, given the same computational resource constraints. The improvement in accuracy offered by the 2D-CNNs has a tradeoff of slower prediction speed, which weakens their relative suitability for use in real-time applications. However, we observe that by reducing the size of the input supplied to the 2D-CNNs, we can improve their prediction speed whilst maintaining higher accuracy than other simpler models.