Probability model based bus travel time modeling method

Abstract

The invention discloses a probability model based bus travel time modeling method and belongs to the field of smart traffic information processing technology. The method includes collecting and processing operation data of a bus; performing fitting on travel time of a segment between stations by utilizing offset lognormal distribution; modeling a queue waiting to enter a station into a first-in first-out queue based on interaction behaviors of buses of different lines in the same station, and modeling a bus station stopping time based on a probability model; obtaining route travel time of thebus according to the segment travel time and the station stopping time and analyzing the distribution, expectation, variance and reliability of the travel time. The method provided by the invention issuitable for bus travel time predication and is accurate in predication results. The method can analyze causes of travel time fluctuation so as to improve public traffic service level.

Description

technical field [0001] The invention belongs to the technical field of intelligent traffic information processing, in particular to a method for modeling the travel time of public transport vehicles based on a probability model. Background technique [0002] At present, in the face of ever-increasing urban traffic demand, road congestion, air pollution, and limited land resources, many cities have begun to implement the travel concept of "transit city". People reduce private car travel and choose urban public transport instead. The reliability of bus travel time is the core element of public transport service level. On the one hand, travel time reliability is an important factor to attract travelers to choose public transport. Travel time prediction is also an important part of the intelligent passenger service system, such as punctuality prediction , delay time prediction and arrival time prediction, etc.; on the other hand, travel time prediction is an important indicator...

AI Technical Summary

Problems solved by technology

[0004] In addition, the existing technology mainly predicts the travel time of private cars through models such as OLS (Ordinary Least Squares), SVR (Support Vector Regression), neural network and deep learning, and the obtained results are predicted values; for the analysis of bus travel time, These prediction techniques cannot analyze the magnitude and cause of bus travel time fluctuations, cannot analyze passenger boarding behavior, and cannot consider the interactive behavior of multi-line buses on the same platform

Images