The rising global e-commerce transactions and the sharp increase in the variety and quantity of goods in e-commerce warehouses inevitably bring new challenges to the storage location assignment. This paper takes movable shelves as the research object, and proposes a method of space allocation based on commodity correlation, while considering the quantity – distance correlation of goods. Aiming at optimizing the correlation of goods and the stability of shelves, an integer programming model was constructed, and an improved NSGA-II algorithm was designed to solve the problem by introducing a learning mechanism combined with the characteristics of the model. Finally, through concrete examples, it is proved that the storage location assignment model and algorithm proposed in this paper can effectively optimize the value of the objective function, improve the picking efficiency by reducing the average handling frequency of the shelves, and provide corresponding management suggestions for the effective operation of the movable shelf storage system.
