基于多源大数据的城市常发性交通拥堵演化规律挖掘及门限控制方法

近年来，城市道路网络有限的承载能力与快速增长的交通需求之间的矛盾尖锐，交通拥堵经常发生。随着通信技术及智慧城市的发展，大量高频、高精度、时空关联的车辆运行轨迹数据以及交通流检测数据被实时获取，这些数据中蕴含着能够描述复杂交通系统运行态势的丰富信息，为人们揭示交通拥堵演化规律及科学管控交通提供了契机。本项目拟融合各种高精度的轨迹数据及交通流检测数据，构建城市路网常发性交通拥堵识别算法，运用深度学习算法预测拥堵的演化趋势，挖掘常发性交通拥堵演化规律；在此基础上，将路网常发性交通拥堵问题转换为优化控制问题，以路网总行程时间最小为目标，运用模型预测控制理论构建门限控制优化模型，运用智能算法对该模型进行求解，计算得到交通拥堵问题的门限控制方案。最后以兰州市安宁区路网为例展开实证研究。研究成果可以为城市常发性交通拥堵的治理提供基础理论支持。

In recent years, the contradiction between the limited carrying capacity of urban road networks and the rapidly growing traffic demand has become increasingly acute, and traffic congestion has often occurred. With the development of communication technology and smart cities, a large number of high-frequency, high-precision, space-time related vehicle trajectory data and traffic flow detection data are acquired in real time. These data contain rich information that can describe the operation situation of complex transportation systems, which provides an opportunity to reveal the evolution regularity of traffic congestion and scientific traffic control. This project intends to integrate various high-precision trajectory data and traffic flow detection data, construct a frequent traffic congestion recognition algorithm for urban road network, and use deep learning algorithm to predict congestion. The evolutionary trend is to explore the evolution regularity of the frequent traffic congestion. On this basis, the road network constant traffic congestion problem is transformed into the optimal control problem. The minimum total travel time of the road network is the target, and the model predictive control theory is used to construct the gating control optimization model, and the intelligent algorithm is used to solve the model, and calculate the gating control scheme for traffic congestion problems. Finally, an empirical study is carried out with the road network of Anning District, Lanzhou City as an example. The research results can provide basic theoretical support for the management of urban traffic congestion.