Travel time estimation on a freeway using Discrete Time Markov Chains

Travel time is widely recognized as an important performance measure for assessing highway operating conditions. There are two methods for obtaining travel time: direct measurement, or estimation. For the latter, previously developed models tend to underestimate travel times under congested conditions because of the difficulties of calculations of vehicle queue formations and dissipations. The purpose of this study is to develop a model that can estimate travel time on a freeway using Discrete Time Markov Chains (DTMC) where the states correspond to whether or not the link is congested. The expected travel time for a given route can be obtained for time periods during which the demand is relatively constant. Estimates from the model are compared to field-measured travel time. Statistical analyses suggest that the estimated travel times do not differ from the measured travel time at the 99% confidence level.