Average travel speed estimation using multi-type floating car data

Abstract

Average travel speed is one of the most important indexes for traffic status identification. This paper presents a model to estimate average travel speed based on the data from multi-types floating cars (i.e., taxis, buses, and logistic vehicles). The concept of dynamic road section integration has been proposed to contend with critical issues such as small sample size and large sampling interval. To evaluate the effectiveness of the proposed approach, this paper has also tested the model performance with simulated data from the microscopic simulator VISSIM. Intensive numerical experiments revealed that the average errors of the estimated average speed are less than 7%, which indicates the proposed approach could improve the estimation accuracy significantly.