基于仿真驱动的高速公路主动限速效用评价与推荐

传统的路侧被动限速方式对于特定的惩处区域以外缺少管控，间接导致车辆行为在时空上的不一致性甚至突变，影响了交通的通行效率与安全性。从车侧主动限速方式入手，提出主动限速效用评价与推荐方法，结合道路线形、交通流量、车型比例，开展多情景主动、被动限速交通仿真，利用安全间接分析模型及交通流运行状态，从安全与效率2个层面提取效用评价指标及其权重，采用集成学习方法进行预测分析。结果显示：主动限速方式相较于被动限速方式更有利于提高安全性和调节效率，而在主动限速方面，GBDT(gradient boosting decision tree)回归模型的预测稳定性和准确率更高(R²=0.984)。

Simulation-driven Based Utility Evaluation and Recommendation of Expressway Proactive Speed Limit

Outside the specific punishment area, the traditional roadside passive speed limit mode lacks traffic management, and thus which indirectly leads to the inconsistency or even sudden change of vehicle behaviors in time and space, thereby affects the traffic efficiency and safety. Focusing on the proactive speed limit mode at vehicle side, a utility evaluation and recommendation method is proposed, which carries out the multi-scenario traffic simulation for varied proactive and passive speed limit considering road line types, traffic flow and vehicle type proportion. From the two perspectives of safety and efficiency, the utility evaluation indicators and weights are extracted through surrogate safety assessment model and traffic flow operation status, and the integrated learning method is used in further prediction and analysis. The results show that the proactive speed limiting mode can improve the safety and adjusting efficiency. In proactive speed limit, the prediction stability and accuracy of GBDT (gradient boosting decision tree) regression model are higher (R²=0.984).