The invention relates to a solution based on the Internet of Things and the big data information technology, in particular to a deep neural network, which comprises the following steps of: acquiring short-time and long-time historical data of road network traffic flow, and performing deep learning by using a Node2vec and graph multi-attention neural network (GMAN) fusion mechanism; training a prediction model, predicting the traffic flow states of the target road section and nodes of the road network for 30 minutes after the current time point, and carrying out the real-time intelligent feedback of the green signal ratio of the signal lamp according to the prediction result, thereby achieving the purposes of precisely limiting the flow, mining the traffic capacity of the road network to the maximum degree, and reducing the congestion and traffic paralysis caused by an accident. According to the method, traffic data acquisition and conversion are converted into adjustment and control ofthe traffic signal lamps, a set of complete method for maximizing the traffic capacity of the key road is formed, application verification is carried out in actual engineering, and the effects of accurate flow limiting, maximum excavation of the traffic capacity of the road network and reduction of congestion and traffic paralysis caused by accidents are achieved.

    本发明涉及一种采用基于物联网、大数据信息技术尤其是深度神经网络的解决方案,通过采集路网交通流短时与长时段历史数据,运用Node2vec与图多注意力神经网络(GMAN)融合机制的深度学习,训练出预测模型并预测出当前时间点之后30分钟路网目标路段和节点交通流状态,并根据预测结果对信号灯的绿信比作实时智能反馈,从而达到精准限流、最大化挖掘路网通行能力、减少事故造成的拥堵和交通瘫痪的目的。本发明从交通数据采集和转换到交通信号灯的调整控制,形成了一套完整的最大化关键道路通行能力的方法,并在实际工程上进行了应用验证,达到了精准限流、最大化挖掘路网通行能力、减少事故造成的拥堵和交通瘫痪的效果。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Method for maximizing traffic capacity of key road based on traffic flow prediction


    Weitere Titelangaben:

    一种基于交通流预测的最大化关键道路通行能力的方法


    Beteiligte:
    WAN HAIFENG (Autor:in) / LI NA (Autor:in)

    Erscheinungsdatum :

    2020-11-03


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    Road traffic flow prediction method

    HOU JIA / CHENG XIAOMING / GUO LICHAO et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Urban road traffic flow prediction method

    ZHANG HUIZHEN / YAO SHUILIN / FENG WENJUAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Road network dynamic traffic distribution method based on traffic flow prediction

    LI XU / ZUO JINPENG / YANG SHIHUAI et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Road traffic flow prediction method and system

    LI JUN / CHEN HUICHUAN / LI GUOQIANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff