A hybrid metaheuristic algorithm for dynamic heterogeneous vehicle routing problem with stochastic demand considering environmental aspects

Energy shortages and environmental pollution drive the development of green and low-carbon logistics transportation models. In this paper, a novel dynamic heterogeneous vehicle routing model is introduced to address these challenges, which converts energy consumption and carbon emissions into green costs under different customer demands. To effectively solve the model, a hybrid adaptive nutcracker optimization algorithm with Lévy differential evolution (ANOA-LD) is proposed. Then, three case studies were conducted to analyze changes in carbon emissions and costs under different carbon emission policies based on distinct customer points. The results indicate that carbon emission policies are pivotal in determining the efficacy of carbon reduction in vehicle routing planning. In addition, an experimental plan was developed, initially verifying model feasibility with random data and later assessing algorithm performance using the Solomon benchmark on a larger scale. Different levels of dynamism were tested for dynamic customer information changes, further validating the effectiveness and superiority of the algorithm. These insights provide valuable guidance for decision-making in green vehicle routing planning.