Time-space correlation-based urban traffic flow prediction method

Abstract

The invention belongs to the field of intelligent transportation, and in particular relates to a method for predicting urban traffic flow based on time-space correlation. The method includes the following steps: 1) forecasting model training: generate corresponding forecasting models according to different time forecasting granularities; 2) real-time traffic forecasting: consistent with the model training process, the latest collected traffic will be used for traffic flow forecasting The data is added to the input end of the forecasting model, and then processed by the forecasting model to output the forecasted traffic for the next period. The invention accurately predicts urban road traffic flow, can realize intelligent traffic control and management, traffic information service, and provides real-time data for alleviating urban traffic congestion, and has significant social and economic benefits.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and in particular relates to a method for predicting urban traffic flow based on time-space correlation. Background technique [0002] The state change of urban road traffic flow is a real-time, nonlinear, high-dimensional, non-stationary process with randomness and uncertainty. The shorter the statistical time, the stronger the randomness and uncertainty. In addition, it is also closely related to factors such as travel demand, upstream and downstream traffic, holidays, weather changes, traffic accidents, and road environment, which brings great difficulties to the prediction of traffic flow. Although the traditional historical average method, time series method, and Kalman filter are simple to implement, the prediction accuracy drops sharply in the case of complex road conditions; while the prediction methods based on nonlinear system theory wavelet analysis, catastrophe theory, and ch...

AI Technical Summary

Problems solved by technology

In addition, it is also closely related to factors such as travel demand, upstream and downstream flow, holidays, weather changes, traffic accidents, and road environment, which brings great difficulties to the prediction of traffic flow.

Although the traditional historical average method, time series method, and Kalman filter are simple to implement, the prediction accuracy drops sharply in the case of complex road conditions; while the prediction methods based on nonlinear system theory wavelet analysis, catastrophe theory, and chaos theory can be compared It simulates the nonlinear characteristics of the system well, and the accuracy is relatively high, but the calculation is complicated, the theoretical basis is not yet mature, and it is difficult to popularize

Images