The invention relates to a traffic flow combination prediction method. The method comprises the following steps: S1, acquiring traffic flow data; s2, performing complete set empirical mode decomposition on the data to obtain a plurality of components with different stability and random features and a residual component; s3, calculating randomness and complexity of all the components obtained in the S2, and dividing all the components into two types according to a calculation result, namely a linear part and a nonlinear part; s4, inputting a component corresponding to the nonlinear part into the trained attention mechanism-time convolution network-bidirectional gating circulation unit neural network model to obtain a prediction result; s5, inputting a component corresponding to the linear part into an autoregressive translation average model to obtain a prediction result; and S6, adding the prediction result of S4 and the prediction result of S5 to obtain a final prediction result. Compared with the prior art, the method has the advantages of higher prediction accuracy and the like.
本发明涉及一种交通流组合预测方法,方法包括以下步骤:S1、获取交通流数据;S2、将数据进行完备集合经验模态分解,得到多个稳定性和随机特征不同的分量和一个残差分量;S3、对S2得到的所有分量计算随机性和复杂度,并根据计算结果将所有分量分为两类,分别是线性部分和非线性部分;S4、将非线性部分对应的分量输入训练好的注意力机制‑时间卷积网络‑双向门控循环单元神经网络模型中,得到预测结果;S5、将线性部分对应的分量输入自回归平移平均模型,得到预测结果;S6、将S4的预测结果和S5的预测结果进行加和,得到最终的预测结果。与现有技术相比,本发明具有预测准确性更高等优点。
Traffic flow combination prediction method
一种交通流组合预测方法
2023-11-14
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Improved adaptive traffic flow combination prediction method
European Patent Office | 2024
|Traffic flow prediction method based on improved combination model and application
European Patent Office | 2022
|European Patent Office | 2021
|