INTEGRATING DIGITAL TWIN AND BARCODE TECHNOLOGIES FOR PREDICTIVE AND COMPARE INVENTORY OPTIMIZATION IN  PUBLIC UTILITY WAREHOUSES

Pavid Ittiwhipat; Surajet Khonjun; Repeepan Pitakaso; Arunrat Sawettham

Proceedings of ICLT 2025

INTEGRATING DIGITAL TWIN AND BARCODE TECHNOLOGIES FOR PREDICTIVE AND COMPARE INVENTORY OPTIMIZATION IN PUBLIC UTILITY WAREHOUSES

Pavid Ittiwhipat; Surajet Khonjun; Repeepan Pitakaso; Arunrat Sawettham

Faculty of Management Science, Ubon Ratchathani University, Thailand; Faculty of Management Science, Ubon Ratchathani University, Thailand; Faculty of Management Science, Ubon Ratchathani University, Thailand; Faculty of Management Science, Ubon Ratchathani University, Thailand

International Conference on Logistics & Transport 2025, Tokyo, Japan, pp. 148-154

Download PDF | View interactive page

Abstract

Purpose: This study aims to address the operational limitations of centralized Enterprise Resource Planning (ERP) systems in public utility warehouses by examining the effectiveness of a localized Warehouse Management System (WMS) integrated with Digital Twin (DT), QR Code tracking, and M a c h i n e L e a r n i n g ( M L ) f o r e c a s t i n g . Design/Methodology/Approach: A quasi-experimental pretest–posttest design was employed across eight regional warehouses operated by Thailand’s Provincial Electricity Authority (PEA). Six months of historical SAP ERP data were compared with two months of post-implementation WMS data. The prototype system integrated QR-based asset tracking, DT simulation for operational optimization, and ML models (Random Forest and LSTM) for workload forecasting. Statistical analysis included t-tests, effect size measurement, and evaluation of predictive models against baseline f o r e c a s t i n g m e t h o d s . Findings: The localized WMS demonstrated significant improvements, with an average processing time decrease of 28.9%, an increase in inventory accuracy from 96.5% to 98.8%, and a 47.3% reduction in error rates. Inventory turnover improved by 15.6%. In predictive analytics, ML models outperformed baseline moving averages, with the LSTM achieving a 20.8% reduction in MAE and a 17.8% reduction in RMSE, enhancing resource allocation and demand planning. Originality / Value: This study provides one of the first empirical evaluations of integrat

Keywords

Digital Twin; Warehouse Management System; QR Code; Machine Learning; Supply Chain Decoupling; Public Utility Logistics

Citation

Pavid Ittiwhipat; Surajet Khonjun; Repeepan Pitakaso; Arunrat Sawettham (2025). INTEGRATING DIGITAL TWIN AND BARCODE TECHNOLOGIES FOR PREDICTIVE AND COMPARE INVENTORY OPTIMIZATION IN PUBLIC UTILITY WAREHOUSES. Proceedings of the International Conference on Logistics & Transport (ICLT 2025), Tokyo, Japan, pp. 148-154.