The invention relates to a short-time traffic flow prediction method and device considering spatial-temporal correlation and a storage medium, and the method comprises the steps: firstly considering the spatial correlation of traffic flow, screening nearby detection stations related to a prediction station through employing a KNN algorithm, and constructing a data set through the traffic flow sequence of the selected detection stations; inputting the constructed time sequence historical traffic flow data into the LSTM neural network for training and testing by considering the time correlation of the traffic flow; and finally, verifying the provided short-term prediction method through real historical traffic data. According to the method, the spatial correlation of the traffic flow data is fully utilized, and the prediction precision of the short-time traffic flow is improved; meanwhile, the LSTM neural network model is introduced, and the time correlation of the traffic flow data is fully utilized, so that the prediction precision of the short-time traffic flow is improved. The method has relatively high accuracy and relatively good practicability in actual traffic flow prediction, and rapid and accurate short-time traffic flow prediction can be realized.

    本发明涉及一种考虑时空相关性的短时交通流预测方法、装置及存储介质,该方法包括首先考虑交通流的空间相关性,采用KNN算法筛选与预测站点相关的附近检测站点,并以所选检测站点的交通流序列构造数据集;接着考虑交通流的时间相关性,将所构造的时序历史交通流量数据输入到LSTM神经网络进行训练与测试;最后通过真实历史交通数据对提出的短时预测方法进行验证。本发明充分利用交通流数据的空间相关性,提高了短时交通流的预测精度;同时引入LSTM神经网络模型,充分利用交通流数据的时间相关性,以此提高短时交通流的预测精度。本发明在实际交通流量预测中具有较高的准确性和较好的实用性,可以实现快速、准确的短时交通流预测。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Short-term traffic flow prediction method and device considering spatial-temporal correlation, and storage medium


    Weitere Titelangaben:

    考虑时空相关性的短时交通流预测方法、装置及存储介质


    Beteiligte:
    FANG DONG (Autor:in) / WU KE (Autor:in)

    Erscheinungsdatum :

    2022-03-29


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS