The Internet of Vehicles (IoV) is an application of the Internet of Things (IoT) in the Intelligent Transportation System (ITS) of smart cities. Many vehicles access the network randomly and handover frequently between access Base Stations (BS), so the flexibility and scalability of the network architecture are required for the IoV network. SDN is a centralized network architecture that has obtained a lot of attention in the IoV. Vehicles share information through the IoV network, and vehicles have high requirements for the real-time and bandwidth of shared information. Network traffic estimation is very important for network management, load balancing, and network planning. The estimation results can be used to improve the quality of service of operators. To estimate the network traffic accuracy and efficiency, we use the Wavelet Decomposition (WD) method to decompose the signal into the Low- and High- frequency component. The low-frequency component of network traffic describes the smoothness and long-range correlation of network traffic, we train an Artificial Neural Network (ANN) model to estimate it. Otherwise, the high-frequency component of the network traffic fluctuates strongly which shows the randomness of the network traffic, we model the network traffic as an exponential distribution. However, there are differences between estimation results and actual network traffic, so we propose an objective function to optimize the network traffic estimation to reduce the errors. Finally, we perform some simulations and the simulation results show that our proposed scheme is feasible.

车联网 (IoV) 是物联网 (IoT) 在智慧城市智能交通系统 (ITS) 中的应用。许多车辆随机接入网络并在接入基站（BS）之间频繁切换，因此车联网网络需要网络架构的灵活性和可扩展性。SDN 是一种集中式网络架构，在车联网中获得了很多关注。车辆通过车联网网络共享信息，车辆对共享信息的实时性和带宽要求很高。网络流量估计对于网络管理、负载均衡和网络规划非常重要。估计结果可用于提高运营商的服务质量。为了估计网络流量的准确性和效率，我们使用小波分解 (WD) 方法将信号分解为低频和高频分量。网络流量的低频分量描述了网络流量的平滑度和长程相关性，我们训练人工神经网络（ANN）模型来估计它。否则，网络流量的高频分量波动很大，表明网络流量的随机性，我们将网络流量建模为指数分布。然而，估计结果与实际网络流量存在差异，因此我们提出了一个目标函数来优化网络流量估计以减少错误。最后，我们进行了一些仿真，仿真结果表明我们提出的方案是可行的。