Short-term traffic flow prediction method and system based on hybrid deep learning and devices

Abstract

The invention belongs to the field of intelligent transportation, particularly relates to a short-term traffic flow prediction method and system based on hybrid deep learning and devices and aims to solve the problem of low precision of an existing large-scale traffic flow prediction method. The method of the invention comprises a step of acquiring historical traffic flow data of each traffic observation point to be predicted, wherein the historical traffic flow data is r traffic flow data sets of continuous equal-time-length periods before a t moment, a step of merging the historical trafficflow data in each traffic flow data set to obtain corresponding merged data and normalizing each merged data, a step of obtaining a normalized prediction result of each traffic observation point at the t moment by adopting a hybrid deep learning model based on the normalized historical traffic flow data of each traffic observation point, and a step of carrying out reverse normalization on the prediction result to obtain a traffic flow prediction value of each traffic observation point at the t moment. According to the invention, the precision of large-scale traffic flow prediction is improved.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and in particular relates to a short-term traffic flow prediction method, system and device based on hybrid deep learning. Background technique [0002] Accurate and efficient traffic flow forecasting is crucial for traffic management and control, which can help alleviate urban traffic congestion, save energy and reduce emissions. Traffic flow prediction has a long research history. As early as the 1970s, the ARIMA model was used to predict short-term traffic flow. ARIMA is the differential autoregressive summation moving average model, which is a widely used time series model. This model can achieve high prediction accuracy when applied to real-time prediction of short-term traffic flow. However, the solution process of this model is to solve the historical time series of each observation point through offline solution equations. The parameters of the solution are relatively fixed, wh...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem of low accuracy of existing large-scale traffic flow forecasting methods, the first aspect of the present invention proposes a short-term traffic flow forecasting method based on hybrid deep learning. include:

Images