Research on optimization model of rural e-commerce distribution efficiency and cost under smart logistics framework

Abstract

Abstract Despite advancements in information technology, rural e-commerce distribution continues to struggle, characterized by inefficient capacity resource allocation and exorbitantly high logistics costs. These challenges severely impede the growth of the rural e-commerce industry and the economic performance of logistics and distribution firms. This study delves into the specific dynamics of rural e-commerce logistics and the prominent issue of the “last kilometer” bottleneck. It constructs a multi-objective planning model aimed at minimizing both distribution costs and time, incorporating constraints such as the load capacity of distribution vehicles, as well as the number and routes of service vehicles. Utilizing the simulated annealing algorithm, this research addresses the shortcomings of genetic algorithms, particularly their tendency to converge on local optima. This enhancement enables the genetic algorithm to effectively identify optimal solutions for distance, cost, and profit within the operational constraints of rural e-commerce distribution. The model’s efficacy was validated and subsequently applied to a case study involving a rural e-commerce enterprise in a county. The findings reveal that the combined genetic algorithm-simulated annealing (GA-SA) approach yields an average optimal solution error of 0.25 and an average solution error of 0.46. Furthermore, the optimized distribution strategy for the four vehicles resulted in total travel distances of 47.46 km, 40.47 km, 28.36 km, and 3.1 km, respectively, culminating in a substantial reduction of 61.29 km compared to the pre-optimization scenario. The reduced iteration count of the algorithms also contributes to enhanced profit outcomes. This research offers valuable insights for rural e-commerce distribution companies seeking to bolster their market competitiveness through upgraded information technology, reasonable resource allocation, cost efficiencies, and enhanced operational effectiveness.