An object-oriented evaluation framework for dynamic vehicle routing problems under real-time information

The dynamic vehicle routing problems (DVRP) is an extension of vehicle routing problems (VRP) in order to consider possible variations of travel times in the network. In this research, a two-stage framework for solving dynamic vehicle routing problem is proposed. In the first stage, the sweep method is adopted in vehicle assignment. In the second stage, a tabu search algorithm is implemented to improve routes under real-time information. The framework is implemented in an object-oriented approach and possible benefit from real-time information is illustrated through numerical simulation. The simulation-assignment model, DynaTAIWAN is applied in numerical simulation to evaluate real-time routing strategies in a traffic network. Numerical experiments are conducted in a 50 Nodes Network and a Taichung City. The results show that positive benefits could be achieved through utilization of real-time information with careful design.

► The fleet management problem is explored in vehicle assignment and real-time route updating.
► The vehicle assignment is accomplished through a classical algorithm: the sweep method.
► The real-time updating algorithm is developed through tabu search algorithm to consider possible dynamic variations of link travel times.
► A simulation-assignment model, DynaTAIWAN, is applied to provide traffic simulation and assignment capabilities under mixed traffic flow conditions.
► The framework provides a practical tool for the evaluation of vehicle routing strategies under real-time information.