A Data-Driven Evolutionary Algorithm for Dynamic Vehicle Routing Problems With Time Windows Under Limited Computational Time

The Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) is a widespread real-world challenge, and numerous algorithms have been proposed to address it. However, in the context of an emerging logistics paradigm, namely the instant delivery, the performance of existing algorithms tailored for DVRPTW degrades significantly, as instant delivery allows only very limited computational time for solving DVRPTW instances. Owing to the periodic nature of customer orders, this paper proposes a data-driven evolutionary algorithm (DDEA) for solving DVRPTW under limited computational time. In the offline phase, a set of generalized solutions is derived from historical data via a dedicated evolutionary algorithm. These solutions are then directly employed in the online phase to construct high-quality solutions for new problem instances. By leveraging these precomputed generalized solutions, DDEA effectively operates within tight time constraints. Extensive experiments using synthetic and real-world data demonstrate that DDEA outperforms five state-of-the-art algorithms designed for DVRPTW under limited computational time, particularly under extremely short time constraints. Note to Practitioners—This paper proposes a data-driven evolutionary algorithm, DDEA, to solve Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) under limited computational time, a critical challenge in instant delivery services. DDEA utilizes historical data to generate generalized solutions during an offline phase, which are then efficiently deployed to construct high-quality routes for real-time request scenarios. Experimental results demonstrate that DDEA outperforms state-of-the-art algorithms, particularly when the computational time is severely limited. Practitioners in instant delivery services can benefit from integrating DDEA into their routing optimization systems to efficiently construct high-quality delivery routes. Future research can explore further enhancements and integration with real-time data.