The invention discloses an improved self-adaptive traffic flow combined prediction method, which comprises the following steps of: 1, improving a variational mode decomposition algorithm by using a KL divergence and frontier energy entropy principle, and decomposing an original traffic flow sequence into a series of relatively stable high and low frequency component sequences; 2, taking the decomposed traffic flow sequence as the input of a graph attention network, calculating an attention coefficient between nodes by using an attention mechanism, extracting dynamic spatial characteristics, and realizing traffic flow sequence spatial correlation modeling; 3, training each bidirectional gating cycle unit (BiRGU) by using an improved Adam optimization algorithm, and constructing each BiGRU network prediction model with optimal performance; and 4, taking the weighted component sequence of each node as the feature input of the gating circulation unit network, and carrying out superposition summation and reverse normalization processing on each prediction value to obtain a final prediction result. The traffic flow sequence can be effectively predicted, and the prediction precision of the traffic flow is improved.

    本发明公开了一种改进的自适应交通流组合预测方法,包括:1、使用KL散度和边锋能量熵原理改进变分模态分解算法,将原始交通流量序列分解为一系列相对平稳的高低频分量序列;2、将分解后的交通流量序列,作为图注意力网络的输入,利用注意力机制计算各节点之间的注意力系数,提取动态空间特征,实现交通流序列空间相关性建模;3、使用改进后的Adam优化算法对各双向门控循环单元(BiRGU)进行训练,构建性能最佳的各BiGRU网络预测模型;4、将各节点加权后的分量序列作为门控循环单元网络的特征输入,并将各预测值叠加求和,反归一化处理得到最终预测结果。本发明可以有效预测交通流量序列,并提高交通流量的预测精度。


    Access

    Download


    Export, share and cite



    Title :

    Improved adaptive traffic flow combination prediction method


    Additional title:

    一种改进的自适应交通流组合预测方法


    Contributors:
    YIN LISHENG (author) / SHI CHENG (author) / LIU PAN (author) / LI TONG (author)

    Publication date :

    2024-04-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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 / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Traffic flow combination prediction method

    XIONG HAO / ZHANG LI | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on improved combination model and application

    YIN LISHENG / LIU PAN / WU YANGYANG et al. | European Patent Office | 2022

    Free access

    Short-time traffic-flow combination prediction method

    YANG CHUNXIA / FU YIQIN / WU WENLU et al. | European Patent Office | 2015

    Free access

    A Short-Term Traffic Flow Combination Prediction Model with Adaptive Weights

    Sun, Chuanxia / Sun, Xiaoliang / Yin, Peixuan et al. | TIBKAT | 2020


    A Short-Term Traffic Flow Combination Prediction Model with Adaptive Weights

    Sun, Chuanxia / Sun, Xiaoliang / Yin, Peixuan et al. | ASCE | 2020