Abstract: Edge computing is one of the key technologies in 5G networks, it can collect and process data on the access network and decrease the transmission load of the network. The data exchange in the Edge computing network Software Defined Networking (SDN) decouples the control plane and forwarding plane in traditional switches and plans routing in the global view, making network management more flexible and efficient. The accurate and comprehensive network traffic measurement is the key to traffic management of edge computing network. Then, we propose a novel edge computing network traffic measurement approach to SDN. Our scheme uses the coarse-grained measurement based on SDN architecture by collecting statistics in Open Flow-based switch and utilize the autoregressive moving average (ARMA) model to infer the fine-grained measurement. In order to decrease the estimation error, we construct an objective function to optimize the estimation results. However, the objective function is an NP-hard problem, then we propose to use a heuristic algorithm to obtain the optimization results. Finally, we conduct a series of simulations to evaluate the performance of the proposed scheme. Simulation results show that our approach is feasible and has a low measurement cost.