On Reconstruction and Prediction of Network Traffic in Software Defined Networking

Abstract

Traffic reconstruction and prediction are important for performance analysis and network planning in networks. Compared with traditional networks, Software Defined Networking (SDN) is a new technology that decouples the control plane and data plane of network switching equipment, making network measurement and management flexible. The SDN architecture of the flow-based forwarding idea brings forth a promising of network traffic capture and prediction. We introduce the principle of SDN traffic measurement and the traffic sampling algorithm. Then, based on time series analysis theory and regressive modeling approach, we propose a lightweight traffic reconstruction and prediction algorithm for SDN applications, which reduces overhead and improves measurement accuracy. Finally, sufficient experiments are presented and designed to validate the proposed method. Simulation results show that our method is feasible and effective.