Stochastic Models of Traffic Flow Interrupted by Incidents

We consider congestion that is caused by irregular occurrences such as traffic accidents, disabled vehicles, adverse weather conditions, spilled loads and hazardous materials. Due to these unexpected events, travel times on the roadways are uncertain. In this paper, we present stochastic models for traffic flow that incorporates uncertain conditions. These models include queueing systems in which customers experience service interruptions from time to time. When a traffic incident happens, either all lanes or part of a lane is closed to the traffic. As such, we model these interruptions either as complete service disruptions where none of the servers work or partial failures where servers work at a reduced service rate. Additionally, the affect of congestion on the traffic flow is also considered. These models are then utilized in estimating the travel times. We present traffic simulation results to show the validity of stochastic models in travel time estimation.