Answers are grounded in this paper and cite their sources.
In the Robotic Mobile Fulfillment Systems (RMFS) of e-commerce warehouses, there is an urgent need for innovative storage strategies, as traditional methods often fail to integrate new products, leading to significant disarray known as the Storage Location Allocation Problem with New Products (SLAP-NP). This paper introduces a Two-Stage Storage Strategy (TSSS) to circumvent this issue. The first stage identifies the similarity of new products, classifying new products as common or random allocation. The subsequent stage devises a model that takes into account the correlation of all products, coupling with a common/random storage allocation framework. For this, we propose a two-stage solution. In the first stage, K-means is improved based on business categories. It employs the Business Categories K-means (BC-K-means) algorithm, identifying similar situations for products. The subsequent stage proposes the mayfly algorithm bolstered by Fuch Chaotic Mapping and Cauchy-Gaussian variation (FCGMA), optimising the model. The performance of this approach is evaluated through multi-sized numerical experiments, using real-world data from a large e-commerce warehouse in China. TSSS can effectively solve the SLAP-NP compared to other strategies. For medium to large-scale cases, the FCGMA markedly outperforms other algorithms, providing a new solution for large-scale warehousing.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: