Traffic speed dynamic interval short-time prediction method

Abstract

The present invention discloses a traffic speed dynamic interval short-time prediction method with high reliability. The method comprises the following steps: (10) obtaining of traffic speed time series: obtaining the observed value of the traffic speed time series of a target section on a road; (20) obtaining of stationary time series: performing first-order difference operation to convert the traffic speed time series to the stationary time series; (30) calculation of a first-order difference predicted value: calculating a traffic speed first-order difference prediction value in each current time interval according to a traffic speed first-order difference time series prediction model; (40) calculation of a residual error standard deviation prediction value: calculating the residual error standard deviation prediction value in each current time interval according to a residual error item synthetical general autoregression condition heteroscedasticity prediction model; and (50) determination of the traffic speed prediction area of the target section: determining the traffic speed prediction interval of the target section in each time interval according to the traffic speed observed value, the traffic speed first-order difference prediction value and the residual error standard deviation prediction value.

Description

technical field [0001] The invention belongs to the technical field of short-term traffic flow forecasting, in particular to a high-reliability short-term forecasting method for dynamic intervals of traffic speeds. Background technique [0002] Traffic flow speed is one of the important technical indicators of road traffic operation, management and control. Accurate and reliable short-term traffic speed prediction has become an important research content of urban intelligent transportation systems such as route guidance and active traffic control. [0003] A large number of researches have been carried out on the short-term traffic speed prediction technology of road sections at home and abroad. Forecasting methods based on statistical models and technologies such as artificial intelligence have been continuously proposed, and the accuracy of predictions has also been continuously improved. [0004] However, most studies only carry out modeling and evaluation of forecastin...

AI Technical Summary

Problems solved by technology

[0005] In short, the existing problems in the existing technology are: the reliability of short-term traffic speed prediction is low

Images