Yiting Hong
Forecasting & Purchasing & QC Department, The Antigua Group, Peoria, AZ 85382, USA.
*Corresponding author: Yiting Hong
Abstract
The study investigates warehouse capacity optimization under dynamic demand conditions. By introducing predictive modeling, historical data on order volumes, inbound frequency, and inventory fluctuations are analyzed to achieve accurate forecasting and dynamic capacity allocation. A hybrid approach combining time-series analysis and machine learning algorithms is employed to construct the prediction model, while a multi-objective optimization method is used to balance space utilization and operational cost. The research further integrates real-time feedback and adaptive recalibration mechanisms to ensure model robustness under continuous data variation. The results demonstrate that the proposed approach effectively enhances capacity utilization and forecasting accuracy, reduces resource waste, and provides reliable technical support for intelligent warehouse management and sustainable logistics operations, achieving an average 15% improvement in storage utilization and a 12% reduction in energy consumption compared with conventional static allocation strategies.
References
[1] Fu Y, Li J, Cui L, et al. Optimization Study of Electric-Hydrogen Hybrid Energy Storage Capacity in Warehouse Park for Smart Grid. Annals of Data Science. 2025 Feb 2 [Epub ahead of print]. doi:10.1007/S40745-025-00649-1.
[2] Shinji I, Masaki K, Ryu N, et al. A Proposal of Path Planning for Robots in Warehouses by Model Predictive Control without Using Global Paths. IFAC PapersOnline. 2022;55(37):573-8. doi:10.1016/J.IFACOL.2022.11.244.
[3] Anonymous. MHS launches new software, predictive maintenance solutions for warehouses. Modern Materials Handling. 2020;75(4):36.
[4] Ansari M, Smith SJ. Warehouse Operations Data Structure (WODS): A data structure developed for warehouse operations mod-eling. Computers & Industrial Engineering. 2017;112:11-9. doi:10.1016/j.cie.2017.08.009.
[5] Nejad YMA, Ali A, Mohsen A, et al. A Highly Effective Optimization Approach for Managing Reverse Warehouse System Capacity Across Diverse Scenarios. Process Integration and Optimization for Sustainability. 2023;8(2):455-71. doi:10.1007/S41660-023-00388-X.
[6] Xian-hao X, Wei-hong D, Hongxia P. A Robust Optimization of Capacity Allocation Policies in the Third-Party Warehouse. Mathematical Problems in Engineering. 2015;2015:810798.1-810798.10. doi:10.1155/2015/810798.
[7] Yi G, Reklaitis VG. Adaptive model predictive inventory controller for multiproduct warehouse system. Automatica. 2014;50(9):2245-53. doi:10.1016/j.automatica.2014.07.022.
[8] Wang S, Lee W, Chang C. Modeling the consignment inventory for a deteriorating item while the buyer has warehouse capacity constraint. International Journal of Production Economics. 2012;138(2):284-92. doi:10.1016/j.ijpe.2012.03.029.
How to cite this paper
Research on Warehouse Capacity Optimization Methods Based on Predictive Modeling
How to cite this paper: Yiting Hong. (2026). Research on Warehouse Capacity Optimization Methods Based on Predictive Modeling. Engineering Advances, 6(1), 22-26.
DOI: http://dx.doi.org/10.26855/ea.2026.03.005