Urban path travel time forecasting method based on floating vehicle data

Abstract

The invention discloses an urban path travel time forecasting method based on floating vehicle data. The urban path travel time forecasting methods based on floating vehicle data particularly includes the steps of analyzing historical data of a floating vehicle, creating historical traffic rules in a periodic mode, creating default traffic rules by traffic management departments or specialists, providing traffic events such as an input vehicle departure starting point and terminal point, the departure time and the current traffic condition to be matched with the traffic rules, and calculating the travel duration of each candidate path. The floating vehicle data can be excavated effectively, the urban path travel time is forecasted effectively, and the urban path travel time forecasting method based on the floating vehicle data is different from a traditional path travel time forecasting method based on the historical data. The method and the technology are easy to implement, operating conditions can be met easily, the urban path travel time can be forecast so as to guide vehicles to select a travel path reasonably, and the method plays a significant role in relieving urban traffic congestion and is easy to apply and popularize in large and medium cities.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a method for predicting travel time of city routes based on floating car data. Background technique [0002] In the field of intelligent transportation research, how to improve the level of transportation services, many countries and regions have carried out research on urban road travel time prediction, and it has become one of the hot spots of international research. Existing travel time prediction methods mainly focus on predictable events and the impact of special weather on traffic patterns. [0003] The prediction accuracy of the existing urban route travel time prediction methods is not high. If the existing prediction methods can be integrated to form traffic rules, various traffic characteristics are considered in the prediction process, and the travel time of various traffic events can be dynamically adjusted. Influenced weights will greatly improve the accura...

AI Technical Summary

Problems solved by technology

[0003] The prediction accuracy of the existing urban route travel time prediction methods is not high. If the existing prediction methods can be integrated to form traffic rules, various traffic characteristics are considered in the prediction process, and the travel time of various traffic events can be dynamically adjusted. The weight of influence will greatly improve the accuracy of vehicle travel time prediction

Images