The invention discloses an urban road network short-term traffic operation state estimation and prediction method, and the method comprises the following steps: (1) acquiring heterogeneous data, preprocessing the heterogeneous data, and reconstructing a speed field of a research unit by using a GASM algorithm by taking a road section between two signalized intersections of a city as the research unit; (2) constructing an urban road network spatial weight matrix, calculating spatial-temporal correlation between road sections, and identifying and quantifying fragile road sections by adopting TOPSIS; (3) taking an average value of the speed according to the reconstructed research unit speed field and selecting a reasonable fragile road section to construct a space-time characteristic matrix of the urban road network; (4) estimating and predicting the traffic state of the whole road network according to the Bi-ConvLSTM. According to the method, the heterogeneous data is fused to reconstruct the speed field of the research unit, and the prediction limitation caused by a single data source is solved; meanwhile, Bi-ConvLSTM is adopted to consider the traffic speed influence of the upstream and the downstream of the research unit, the space-time characteristics of the traffic flow are fully mined, and the prediction accuracy is further improved.
本发明公开了一种城市路网短期交通运行状态估计与预测方法,包括:(1)获取异构数据并进行预处理,并以城市两信号交叉口之间路段为研究单元,利用GASM算法对研究单元的速度场重构;(2)构建城市路网空间权重矩阵,计算各路段间的时空相关性并采用TOPSIS识别并量化脆弱路段;(3)依据重构后的研究单元速度场取速度的平均值及选取合理脆弱路段构建城市路网的时空特征矩阵;(4)根据Bi‑ConvLSTM对全路网的交通状态进行估计与预测。本发明通过融合异构数据重构研究单元速度场,解决单一数据源导致的预测局限性,同时采用Bi‑ConvLSTM考虑研究单元上游和下游的交通速度影响,充分挖掘交通流的时空特性,进一步提高了预测的准确率等优点。
Urban road network short-term traffic operation state estimation and prediction method
一种城市路网短期交通运行状态估计与预测方法
2020-07-07
Patent
Electronic Resource
Chinese
The Urban Road Short-Term Traffic Flow Prediction Research
Trans Tech Publications | 2013
|METHOD FOR ESTIMATING AND PREDICTING SHORT-TERM TRAFFIC CIRCULATION STATE OF URBAN ROAD NETWORK
European Patent Office | 2021
|Short‐term traffic flow prediction of road network based on deep learning
Wiley | 2020
|