Analysis of Freeway Travel Time Variability Using Bluetooth Detection

Travel time has long been an important performance measure for assessing traffic conditions and the extent of highway congestion. However, recently, more and more attention has been given to understanding the uncertainty regarding the variability in travel time from hour to hour and day to day—variability that is known to be a source of great frustration among road users. In this paper, travel-time variability is studied by collecting travel-time data using probe data on freeway segments in Indianapolis obtained using anonymous Bluetooth sampling techniques. The data show considerable travel-time variability is induced by adverse weather, but also show that variability results from unexpected changes in traffic flow rates and driver behavior. Various statistical models are estimated to understand the effect that traffic-related variables have on variability in individual vehicle travel times as well as average travel times. For individual vehicle travel times, a model is estimated to study how the probability of a vehicle’s duration of time spent on freeway segments changes over time. Interestingly, this model shows that the point where the conditional probability of travel times becoming longer occurs roughly at the onset of level-of-service $F$ conditions—an important finding that supports the traffic-density definitions of level of service $F$ used in the highway capacity manual. Another model, estimated using seemingly unrelated regression estimation, studies 15-min interval average vehicle travel times and the standard deviation of these travel times on the basis of speed and volume (available from remote traffic microwave sensors) and time of day indicators. This model provides interesting insights into the traffic parameters that affect average travel time and its variability.