Urban rail transit short-term passenger flow dynamic prediction method

Abstract

The invention relates to an urban rail transit short-term passenger flow dynamic prediction method. Based on a traditional passenger flow prediction method and actual passenger flow data, the method includes generating a prediction error sequence of the prediction time interval; by means of a reverse cloud generator, establishing a prediction error cloud model, generating a prediction error normalcloud drop distribution diagram by adopting a normal cloud generator, calculating a cloud drop quantile under a given confidence level and a confidence range of possible fluctuation of the passengerflow volume corresponding to the cloud drop quantile by utilizing a quantile principle, and then predicting the passenger flow volume at the next moment according to the uncertainty interval. According to the urban rail transit short-term passenger flow dynamic prediction method provided by the invention, uncertainty analysis of urban rail transit short-term passenger flow prediction can be realized, the short-term passenger flow prediction precision is improved, and a more accurate basis is provided for safety management and operation organization decision of urban rail transit.

Description

technical field [0001] The invention relates to the field of urban rail transit passenger flow forecasting, in particular to a dynamic prediction method applicable to urban rail transit short-term passenger flow. Background technique [0002] With the rapid development of society and economy and the continuous improvement of the level of urban automation, people's travel frequency has increased significantly. Urban rail transit has developed into an important transportation task in many countries and regions, improving urban traffic structure, alleviating traffic demand and A powerful vehicle for supplying contradictions. With the advancement of the network process and the expansion of scale, urban rail transit has highlighted the characteristics of continuous increase in passenger volume, steady increase in passenger flow intensity, and significant passenger traffic effects. Reasonable and accurate passenger flow forecasting can be used for passenger flow induction and safe...

AI Technical Summary

Problems solved by technology

[0003] The passenger flow of urban rail transit has the characteristics of nonlinearity, randomness, and uncertainty. Most of the existing prediction methods are static and deterministic. The prediction methods often have certain deficiencies and defects, resulting in low accuracy of short-term passenger flow prediction.

Images