Bee Colony Optimization for innovative travel time estimation, based on a mesoscopic traffic assignment model

• Performance of a traffic flow model in providing efficient travel time reconstruction.
• Time-discrete, mesoscopic simulation approach, based on discrete vehicle packets.
• New model of network traffic assignment, based on the Bee Colony Optimization.
• Application to a standard network carried out to test the performance of our model.
• Result is a reliable model for prediction process of traveling times within ATIS.

In this article, we propose a framework for travel time prediction based on a time-discrete, mesoscopic traffic flow model, in which the measure of travel time is obtained as a link performance resulting from a dynamic network loading process. The spatiotemporal flow propagation on the road network is simulated incorporating the mesoscopic model and a linear link performance model, based on a travel time function. Acceleration levels are calculated explicitly, as a result of a fixed point problem. The traffic assignment to the network has been carried out through a completely new model, based on the Bee Colony Optimization (BCO) metaheuristics. In comparison with results of simulations carried out by using another mesoscopic model (DYNASMART), the travel times obtained with the proposed method appear more realistic.