An EMD and ARMA-based network traffic prediction approach in SDN-based internet of vehicles

The Internet of Vehicles (IoV) is the application of the Internet of things (IoT) technology in intelligent transportation systems. The vehicle accesses the IoV network through base stations to request the services of intelligent transportation. When a vehicle is driving on the road, it needs to frequently handover BSs, which requires the IoV network to provide highly dynamic and low-latency network access services. The Software Defined Networking (SDN) is a new type of centralized control network architecture with high dynamics and flexibility, and it is also the focus of network architecture research in recent years. We study the IoV network based on SDN. To efficiently manage the network traffic and reduce the data transmission delay, we will model the network traffic and predict the network traffic, to realize the scheduling and management of the network traffic. In this paper, we model the network traffic based on empirical mode decomposition and use the improved autoregressive moving average model to predict the network traffic. Then, we propose an optimization function to reduce the prediction errors of the network traffic model. Finally, we conduct some simulations to verify the proposed measurement scheme and the simulation result shows the feasibility of the proposed prediction method.