Experimental Analysis of the Impacts of Freeway Incidents Using Short-term Traffic Forecasts

抄録

Predictive information on the impacts of freeway incidents can be a critical criterion for users in selecting travel options and for operators in operating transportation systems. If it is provided properly, users can select time-effective routes and operators can effectively run the system. In this study, a model was proposed to estimate and predict freeway incident impacts using a micro-simulation based framework. The predictive model for incident impacts was based on short-term forecasting. The proposed model was examined using techniques such as MARE, MAE, and RMSE. The results of the analysis show that the models are accurate enough to be deployed in the real world. They also suggest that the development of a microscopic incident impact forecasting model proposed in this study would help mitigate the traffic delays in case of incidents and the associated social expenses as well.