基于混合网联车环境下高速公路交通状态估计测试数据
收藏资源简介:
交通状态估计在交通控制和管理中起着基础性的作用。在联网车辆 (CV) 环境中,联网车辆感知和交互的交通相关数据可用于估计交通状态。然而,渗透率较低的情况,从联网车辆收集的数据将是不充分的。同时,采集数据的代表性与渗透率呈正相关。本数据库可用于基于深度学习的交通状态估计算法。具体来说,我们设计了一个KNN数据模型整合加速度数据,解决数据不足的问题。数据集估计的速度将交通状态分为三类:自由流、最佳流和拥塞。SUMO使用数据用于模拟不同渗透率下的交通情况,以评估我们的方案。
Traffic state estimation plays a fundamental role in traffic control and management. In the Connected Vehicle (CV) environment, traffic-related data perceived and interacted by connected vehicles can be used to estimate traffic states. However, when the penetration rate is low, the data collected from connected vehicles will be insufficient. Meanwhile, the representativeness of the collected data is positively correlated with the penetration rate. This database can be applied to deep learning-based traffic state estimation algorithms. Specifically, we designed a K-Nearest Neighbors (KNN) data model that integrates acceleration data to address the problem of insufficient data. The estimated speeds derived from this dataset classify traffic states into three categories: free flow, optimal flow, and congestion. SUMO is employed to simulate traffic scenarios under different penetration rates for evaluating our proposed scheme.




