A data-driven optimization model for the scattered storage assignment with replenishment

Modern warehouses are transitioning from pure storage facilities to order fulfillment centers. To improve order-picking efficiency, picking areas are restricted to small zones to save picker travel distance and thus can only store a limited quantity of SKUs. As a result, replenishment must be frequently carried out which not only causes intensive working efforts but also impacts the order-picking efficiency. Despite of the important role of replenishment, it has been seldom considered in storage assignment planning. This paper proposes a novel optimization model for the storage assignment problem considering both the order-picking and replenishment operations. Instead of the traditional first-extract-then-optimize paradigm, we develop an effective solution method for the problem by integrating the extraction and optimization steps together to avoid the loss of information. Intensive experiments and a case study are presented, the results of which indicate significant advantages of our model against the state-of-the-art counterpart. Several managerial implications are derived: (1) Order data implies substantial useful information for storage assignment planning, including but not limited to the demand correlation of products; (2) The replenishment efforts are intensive and negatively correlated to the order-picking efforts, which therefore should not be neglected in storage assignment planning; (3) To minimize the total working efforts, the optimal replenishment level r of the (r,S) replenishment policy should be more than 0.4S but less than 0.6S with respect to each SKU.