车联网环境下基于模糊逻辑的交通拥堵检测方法

针对现有的道路交通拥堵检测方法的不足,提出了一种基于V2V的道路交通拥堵检测方法。首先基于V2V的方式实时获取邻居车辆状态信息,建立车辆邻居表;其次依据车辆行驶速度、车流密度、交通拥堵评级体系构建模糊控制器,完成本地交通拥堵水平的估计;然后通过车车通信进行邻居车辆交通拥堵状况的查询,并根据大子样假设检验验证本地交通拥堵水平值,完成所在区域交通拥堵水平的检测;最后基于Veins平台搭建仿真测试场景,仿真对比了拥堵检测结果的准确率,同时测试车辆节点的退避时槽数量和接收广播数据包的数量。实验结果表明, 提出的道路交通拥堵检测方法实现的拥堵检测准确率分别比线圈法和CoTEC法提高了5.5%和7.5%;提出的道路交通拥堵检测方法实现的车车通信网络拥塞比CoTEC法降低了90.8%,并且在未发生交通拥堵时通信节点的通信负载显著降低。

Traffic congestion detection method based on IoV and fuzzy logic

Because of the drawback of existing method, the paper proposed a traffic congestion detection method based on Internet of Vehicles and fuzzy logic. Firstly, this method constructed a neighbor table of vehicle based on the obtained real-time information of neighbor vehicles. Secondly, it created a fuzzy controller according to the speed, traffic density and traffic congestion rating system, and evaluated the local traffic congestion level. Thirdly, it realized the inquiry of traffic congestion status of neighbor vehicles based on real-time communication between neighbor vehicles, and verified the local traffic congestion level based on large sub-sample hypothesis test, then completed the detection of regional traffic congestion level. Finally, it built a simulated test scenario based on Veins platform, then it compared the accuracy of detecting traffic congestion, and calculated the backoff slots and received broadcast packets of vehicle nodes in the simulated test scenario. The results show that the accuracy of traffic congestion detection of the proposed method is increased by 5.5% and 7.5% compared with "no trigger" method and CoTEC method, respectively. The proposed method reduces the network congestion of vehicle communication by 90.8% compared with CoTEC method, and the communication load of communication nodes significantly decreases when there is no traffic congestion.