本发明提供一种用于交通控制系统的交通流量预测模型的在线联邦学习方法,包括:D1、对每个路侧单元的交通流量预测模型进行预设次数的更新,每次更新包括:D11、获取当前路侧单元的待预测交通流量序列作为其交通流量预测模型的编码输入以获得其编码隐藏状态;D12、服务器计算当前路侧单元与其他路侧单元之间的空间关系并更新当前路侧单元的编码隐藏状态,将更新后的编码隐藏状态作为当前路侧单元的交通流量预测模型的解码输入以获得预测交通流量;D13、根据实际交通流量和预测交通流量之间的损失更新当前路侧单元的交通流量预测模型的参数;D2、服务器将所有交通流量预测模型的参数进行融合;D3、将融合后的模型参数下发至每个路侧单元以更新每个路侧单元的模型参数。

    The invention provides an online federated learning method for a traffic flow prediction model of a traffic control system, and the method comprises the steps: D1, carrying out the updating of a preset number of times of the traffic flow prediction model of each road side unit, each updating comprises the following steps: D11, acquiring a to-be-predicted traffic flow sequence of the current road side unit as a code input of the traffic flow prediction model so as to obtain a code hiding state of the current road side unit; d12, the server calculates the spatial relation between the current road side unit and other road side units and updates the code hiding state of the current road side unit, and the updated code hiding state serves as decoding input of the traffic flow prediction model of the current road side unit to obtain predicted traffic flow; d13, updating the parameters of the traffic flow prediction model of the current road side unit according to the loss between the actual traffic flow and the predicted traffic flow; d2, the server fuses the parameters of all the traffic flow prediction models; and D3, issuing the fused model parameters to each road side unit to update the model parameters of each road side unit.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    一种交通流量预测模型的在线联邦学习方法


    Erscheinungsdatum :

    2024-06-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen