The invention provides a short-term traffic flow prediction method based on a GWO-Elman neural network, and the method comprises the steps: firstly obtaining a traffic flow data set, carrying out the preprocessing of the data set, and dividing the processed data into a training data set and a test data set; then, a convergence factor optimization GWO algorithm model based on cosine law change is introduced, parameters such as upper and lower bounds are input, data are input into the GWO algorithm model, and whether weight and threshold parameters meet errors or not is judged through a training model; and then establishing an Elman neural network and initializing parameters, inputting the weight and the threshold obtained by the GWO algorithm model into the Elman neural network, inputting the test data set to test the trained Elman neural network, and predicting the traffic flow by using the obtained model. A simulation experiment result shows that the accuracy of a short-time traffic flow prediction result based on the GWO-Elman neural network is higher than that of a traditional prediction method.
本发明提供了一种基于GWO‑Elman神经网络的短时交通流预测方法,该方法首先获取交通流数据集,对数据集进行预处理,将数据处理后分为训练数据集和测试数据集。然后引用基于余弦规律变化的收敛因子优化GWO算法模型,输入上下界等参数,将数据输入GWO算法模型通过训练模型判断权重和阈值参数是否满足误差。接着建立Elman神经网络并初始化参数,将GWO算法模型得到的权重和阈值输入Elman神经网络,输入测试数据集对训练后的Elman神经网络进行测试,采用所得模型对交通流进行预测。仿真实验结果表明,基于GWO‑Elman神经网络的短时交通流预测结果比传统的预测方法准确率更高。
Short-term traffic flow prediction method based on GWO-Elman neural network
基于GWO-Elman神经网络的短时交通流预测方法
2023-11-28
Patent
Electronic Resource
Chinese
IPC: | 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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Short-term traffic flow prediction system based on SARIMA-GA-Elman combined model
European Patent Office | 2021
|Traffic Jam Prediction through Elman Neural Network Based on Monte Carlo Simulation
Trans Tech Publications | 2014
|