Network Prediction with Traffic Gradient Classification using Convolutional Neural Networks
Taejin Ko, Syed M. Raza, Dang Thien Binh, Moonseong Kim, Hyunseung Choo · 2020
Current TCP/IP network infrastructures and management systems are facing a tough time in handling the unusual increase in network traffic due to the surge of typical real-time applications. To solve this problem, management system predicts the changes in network traffic and handle them proactively. In this paper, we convert the traffic prediction into a classification problem and use Convolutional Neural Network (CNN) deep-learning technique to classify the fixed time interval traffic into different classes. We implement the CNN model using Python and Keras library. The proposed algorithm shows higher accuracy (92.6%) and F1 score than the existing Random Forest machine learning method.