SDN Traffic Prediction using Empirical Mode Decomposition

Abstract

Internet traffic prediction is essential for effective network management, resource allocation, and ensuring efficient quality of service. Network resources can be dynamically managed by forecasting future traffic using past traffic patterns. Network traffic prediction enables the dynamic resource allocation to avoid the congestion and conflicts in the network. An Empirical mode decomposition (EMD) based machine learning models were proposed in this paper for the prediction of Software Defined Networks (SDN) traffic. SDN is a modern network architecture which separates the data plane from the control plane to provide centralized control over the network. EMD is an adaptive signal decomposition technique which extracts various frequencies from the collected network traffic at specified sampling intervals which are intrinsic mode frequencies (IMFs). Ensemble machine learning models such as Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were applied on intrinsic mode frequencies to generate the accurate predictions. SDN traffic traces were generated using CAIDA traffic traces and the experimental results suggests that EMD-XGBOOST outperforms than the other models with low root mean squared error (RMSE) and mean squared error (MSE).