The invention relates to an expressway truck flow prediction algorithm, software and device based on a deep reinforcement learning model, and relates to the field of expressway management. The algorithm comprises the following steps: acquiring first data of first vehicle flow of all lanes of a first road section at a t moment; preprocessing the first data to obtain normalized historical data; based on the LSTM model, constructing at least two single deep learning models; dividing normalized historical data into a training set and a test set according to a preset proportion, training the plurality of single deep learning models by using the training set, and determining a prediction error by using the test set; giving different weights to the plurality of single deep learning models based on the prediction error, and constructing a combined deep learning model; and based on the combined deep learning model, outputting the first vehicle flow at the next moment by inputting the first vehicle flow at the historical moment and the current moment. The model is established based on the truck flow data so as to predict the future flow and guarantee the safety of the expressway.

    本申请涉及基于深度强化学习模型的高速公路货车流量预测算法、软件与装置,涉及高速公路管理领域。所述算法包括获取第一路段的所有车道的第一车辆流量在t时刻的第一数据;将所述第一数据进行预处理,得到归一化历史数据;基于LSTM模型,构建至少两个单深度学习模型;将归一化历史数据根据预设比例划分训练集和测试集,利用所述训练集训练多个所述单深度学习模型,利用所述测试集确定预测误差;基于所述预测误差赋予多个所述单深度学习模型不同权重,构建组合深度学习模型;基于所述组合深度学习模型,通过输入历史时刻及当前时刻的第一车辆流量,输出下一时刻的第一车辆流量。本申请基于货车流量数据建立模型,以预测未来流量,保障高速公路安全。


    Access

    Download


    Export, share and cite



    Title :

    Highway truck flow prediction algorithm, software and device based on deep reinforcement learning model


    Additional title:

    一种基于深度强化学习模型的高速公路货车流量预测算法、软件与装置


    Contributors:
    YUAN YUEMING (author) / HUAN HUAN (author) / YIN BOHUA (author) / CAI HUIXING (author)

    Publication date :

    2022-09-27


    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



    Highway On-Ramp Truck Platooning Based on Deep Reinforcement Learning

    Wang, An / Qi, Liang / Luan, Wenjing et al. | Transportation Research Record | 2024


    Deep learning based traffic flow prediction model on highway research

    Jia, Qingyang / Zang, Jingfeng / Liu, Shuanglin | SPIE | 2024


    Highway monitoring method and system based on deep reinforcement learning algorithm

    XU YANJUN / JIA BAIQIANG / HU CHAORAN et al. | European Patent Office | 2022

    Free access

    Deep Reinforcement Learning for Truck-Drone Delivery Problem

    Zhiliang Bi / Xiwang Guo / Jiacun Wang et al. | DOAJ | 2023

    Free access

    Highway short-time traffic flow prediction method based on deep learning

    YAN MIN / ZHOU WEIJIAN | European Patent Office | 2023

    Free access