Average Flow Time Estimation and Its Application for Storage Relocation in an Order Picking System

Abstract

AbstractThis study proposes an average flow time estimation model based on Gaussian process regression that can be applied to adjust the storage locations of partial products and manages demand fluctuations and other dynamic order picking issues. We use the historical order picking data of a progressive zone picking system to extract features for the model. Subsequently, we train the estimation model and acquire the new storage location assignment by relocating part of the total products based on the estimated average flow time from the learning model. We test the proposed model using a simulation model based on a real cosmetic company’s distribution center in South Korea. The simulation results indicate that the proposed model improves the performance by 9.61% with four relocation operations compared with the original storage location assignment before reassignment. The proposed model shows significant effectiveness when workloads are unbalanced, even in environments with high product diversity. We conclude that the proposed model could improve the productivity of real distribution centers with fewer reassignment operations.KeywordsFacility logisticsOrder pickingFlow time estimationStorage location assignmentWarehouse