基于动态图嵌入的车联网拓扑控制

Topology control based on dynamic graph embedding in Internet of vehicles

针对由车联网的高度动态性和复杂性导致网络拓扑难以合理、稳定构建的问题,提出了关于车联网的范围标签图嵌入方法。首先,根据路侧单元分割车辆网络,利用驾驶员辅助系统获取实时车辆信息;其次,使用傅里叶变换、模糊推理对车辆信息预处理,获得车辆低维特征向量,再对新加入网络的车辆节点进行冷启动处理;最后,以所提动态图嵌入方法在区域内进行拓扑控制,充分利用车辆的特征信息构建车联网,实现网络的动态更新。实验结果表明,所提图嵌入方法建立的网络拓扑相对于传统网络及对比图嵌入方法,具有更好的动态性、连通性以及稳健性。

Facing the problem that it was difficult to construct the topology of Internet of vehicles(IoV)reasonably and stably due to the high dynamics and complexity of IoV,a label-range graph embedding(LRGE)method was proposed.First,the vehicular network was divided according to the road side unit(RSU).The driver assistance system was used to obtain real-time vehicle information.Then,the vehicle information was preprocessed by Fourier transform and fuzzy inference system to obtain the low-dimensional feature vector of the vehicles.For the newly joined vehicle nodes,the cold boot processing was carried out.Finally,the proposed dynamic graph embedding method was used to control the topology of the network in the region.Using the vehicle information,the IoV was reconstructed to realize the dynamic update.The experimental results show that the network topology established by the proposed method has better dynamics,connectivity and robustness than the traditional network and comparative graph embedding methods.