A Robust Network Traffic Modeling Approach to Software Defined Networking

Abstract

Software Defined Networking (SDN) architecture satisfies the flexibility and scalability requirements of Internet of Things (IoT) network. A large amounts of IoT data is transmitted and exchanged through IoT network. However, many of services of IoT are sensitive to latency and bandwidth, so the network traffic model and measurement in IoT are different legacy networks. In this paper, we propose a robust network traffic modeling approach and use it to estimate network traffic in IoT. To obtain the measurement results with low overhead and high accuracy, we model the network traffic as liner function with noise. Then, we collect the statistics of coarse-grained traffic of flows and fine-grained traffic of links, and use the robust network traffic model to forecast the network traffic with the coarse-grained measurement of flows. In order to optimize the estimation results, we propose an optimization function to decrease the estimation errors. Since the optimization function is NP-hard problem, then we use a heuristic algorithm to obtain the optimal solution of the fine-grained measurement. Finally, we conduct some simulations to verify the proposed measurement scheme. Simulation results show that our approach is feasible and effective.