强化学习在交通流预测中的应用研究

Application of Reinforcement Learning in Traffic Flow Prediction

交通流预测是智能交通管理的核心环节之一,对于实现精准调度、优化交通流动具有至关重要的作用。然而,由于交通系统的复杂性和不确定性,传统的交通流预测方法往往难以满足对准确性和实时性的要求。基于此,文章提出一种基于强化学习的交通流预测方法,并使用METR-LA数据集对这一方法进行验证。结果表明,该方法在不同场景下展现了良好的预测性能,有效适应了城市交通系统的时空动态变化。

Traffic flow prediction is one of the core links of intelligent traffic management,which plays a vital role in realizing accurate scheduling and optimizing traffic flow.However,due to the complexity and uncertainty of the traffic system,the traditional traffic flow forecasting methods are often difficult to meet the requirements of accuracy and real-time.Based on this,this paper proposes a traffic flow prediction method based on reinforcement learning,and uses METR-LA data set to verify this method.The results show that this method shows good prediction performance in different scenarios,and effectively adapts to the spatio-temporal dynamic changes of the urban transportation system.