Travel Time Prediction Methods for Dynamic Incident Handling”

Effective travel time prediction is of great importance for efficient real-time management of freight deliveries, especially in urban networks. This is due to the need for dynamic handling of unexpected events, which is an important factor for successful completion of a delivery schedule in a predefined time period. This chapter discusses the prediction results generated by two travel time estimation Methods that use historical and real-time data respectively. These methods are incorporated by the real-time fleet management system for the prediction of arrival time to the remaining customers. The first method follows the k-nn model, which relies on the non-parametric regression method that was analyzed, whereas the second one relies on an interpolation scheme which is employed during the transmission of real-time data in fixed intervals. The study focuses on exploring the interaction of factors that affect prediction accuracy by modeling both prediction methods. The data employed are provided by real-life scenarios of a freight carrier and the experiments follow a 2-level full factorial design approach