Development and Implementation of Dimensional Weight Algorithms for Improved Efficiency in Warehouse Management Systems

Abstract

Refining dimensional weight assessment is vital for improving warehouse management effectiveness, especially in the logistics and e-commerce sectors. Conventional approaches to calculating dimensional weight frequently cause either overestimation or underestimation, leading to higher shipping expenses and ineffective storage efficiency. This research seeks to create and apply a dimensional weight optimization algorithm that combines rule-based modeling with machine learning to enhance accuracy and storage efficiency, and lower operational costs. This study uses an experimental method, carried out in January 2025 in Malaysia, to evaluate the efficacy of the proposed algorithm in a Warehouse Management System (WMS). The algorithm is evaluated with live warehouse data, utilizing IoT and cloud computing technologies for smooth integration. Important assessment metrics consist of accuracy in dimensional weight assessment, effectiveness of warehouse storage, and decrease in logistics costs. The results indicate that the suggested algorithm reaches an accuracy of 97.2%, greatly exceeding the conventional method's 89.5%, while lowering the mean absolute error from 2.3 kg to 0.8 kg. Warehouse space usage rises from 75.4% to 89.6%, and processing efficiency grows by 37.5%, boosting total warehouse output. Moreover, operational expenses diminish because of enhanced weight evaluation and better space distribution. Future studies should emphasize the integration of deep learning models for enhanced optimization, experimentation with various product categories, and the inclusion of robotic automation to improve warehouse operations. This research highlights the significance of smart dimensional weight assessment in contemporary warehouse management systems.