Optimization of container transport loading for China–Europe freight trains based on RFID technology

Yingli Zhu; Xiaokun Liu; Tingting Pang

doi:10.61089/aot2025.gh7qmb19

Authors

Yingli Zhu Xi'an Traffic Engineering Institute, School of Traffic & Transportation, Xi’an, China Author https://orcid.org/0009-0002-2577-7767
Xiaokun Liu Group Company Office, China Railway Xi'an Group Co., Ltd., Xi’an, China Author https://orcid.org/0009-0008-0109-9328
Tingting Pang Xi'an Traffic Engineering Institute, School of Traffic & Transportation, Xi’an, China Author https://orcid.org/0000-0001-9144-1386

DOI:

https://doi.org/10.61089/aot2025.gh7qmb19

Keywords:

RFID, Container, Loading optimization, Q-learning algorithm, GA

Abstract

With the rapid development of the global economy, international trade plays a crucial role in the economic growth and resource allocation of various countries. As an important logistics channel connecting China and Europe, the China-Europe Railway Express has significantly contributed to supporting the "Belt and Road" initiative and promoting regional economic cooperation. However, the efficiency of container transportation directly affects the quality of transport and operational costs, thus improving the loading efficiency of container transport has become an urgent issue in modern logistics management. Most existing container transport methods rely on traditional scheduling and loading strategies, which often fail to meet the real-time demands posed by dynamic market changes. This paper proposes a new real-time loading optimization framework based on Radio Frequency Identification (RFID) technology to address the container transport optimization problem for the China-Europe Railway Express. This framework manages real-time cargo requests through task queues and dynamically invokes the Iterative Heuristic Tree Search (IHTS) algorithm by the core decision-making component to generate loading plans and pass them to the execution component. By constructing a data generation model based on a normal distribution, this paper simulates the recognition probability of RFID tags to enhance decision-making accuracy. Experimental results show that the proposed method completed 45 tasks within 60 minutes, which is 50.00% higher than the improved Q-learning algorithm and 28.57% higher than the genetic algorithm based on the Metropolis criterion. In terms of path optimization, the length of the path in this method is 108 meters, significantly shorter than the 125 meters of the improved genetic algorithm and the 141 meters of the Q-learning algorithm. In addition, the total transportation cost of the proposed loading optimization method is 608.28 yuan. This cost integrates the vehicle transportation distance cost, the delay penalty caused by failure to load on time, and other operational losses. Experimental results demonstrate that this real-time loading optimization framework not only significantly enhances container loading efficiency but also effectively reduces operational costs, showing promising application prospects and practical value.

References

1. Abdullahi, M. O., Nageye, A. Y., Ahmed, A. D., & Ahmed, M. M. (2024). Optimizing Port Logistics: Empowering Mogadishu Port with RFID Technology in Somalia. International Journal of Electronics and Communication Engineering, 11(4), 115–120. https://doi.org/10.14445/23488549/IJECE-V11I4P112.

2. Al-Shboul, M. (2023). RFID technology usage effect on enhancing warehouse internal processes in the 3pls providers: An empirical investigation in Jordanian manufacturing firms. Uncertain Supply Chain Management, 11(3), 977–990. https://doi.org/10.5267/j.uscm.2023.5.222.

3. Alzahrani, B. A., & Irshad, A. (2023). An improved IoT/RFID-enabled object tracking and authentication scheme for smart logistics. Wireless Personal Communications, 129(1), 399–422. https://doi.org/10.1007/s11277-022-10103-7.

4. Bansal, S., Goel, R., & Maini, R. (2022). Ground vehicle and UAV collaborative routing and scheduling for humanitarian logistics using random walk based ant colony optimization. Scientia Iranica, 29(2), 632–644. https://doi.org/10.24200/sci.2021.58309.5664.

5. Begić, H., Galić, M., & Klanšek, U. (2024). Active BIM system for optimized multi-project ready-mix-concrete delivery. Engineering, Construction and Architectural Management, 31(12), 5057-5084. https://doi.org/10.1108/ECAM-11-2022-1064.

6. Cammarano, A., Varriale, V., Michelino, F., & Caputo, M. (2023). Blockchain as enabling factor for implementing RFID and IoT technologies in VMI: A simulation on the Parmigiano Reggiano supply chain. Operations Management Research, 16(2), 726–754. https://doi.org/10.1007/s12063-022-00324-1.

7. Casella, G., Bigliardi, B., & Bottani, E. (2022). The evolution of RFID technology in the logistics field: a review. Procedia Computer Science, 200(2), 1582–1592. https://doi.org/10.1016/j.procs.2022.01.359.

8. Chiu, B. H., & Shih, S. C. (2023). The Adoption of RFID for Military Logistics: Which Factors Do Matter in Taiwan? Journal of Economics, Finance and Accounting Studies, 5(3), 215–222. https://doi.org/10.32996/jefas.2023.5.3.17.

9. Dardouri, S., BuHamdan, S., Al Balkhy, W., Dakhli, Z., Danel, T., & Lafhaj, Z. (2023). RFID platform for construction materials management. International Journal of Construction Management, 23(14), 2509–2519. https://doi.org/10.1080/15623599.2022.2073085.

10. Flanagan, J., & McGovern, C. (2023). A qualitative study of improving the operations strategy of logistics using radio frequency identification. Journal of Global Operations and Strategic Sourcing, 16(1), 47–68. https://doi.org/10.1108/JGOSS-04-2021-0030.

11. Groumpos, P. P. (2023). A Critical Historic Overview of Artificial Intelligence: Issues, Challenges, Opportunities, and Threats. Artificial Intelligence and Applications, 1(4), 197–213. https://doi.org/10.47852/bonviewAIA3202689.

12. Guo, J., Wang, Y., Guo, Y., Dai, S., Yan, R., & Shi, Z. (2024). Exploring logistics transport route optimization: An algorithmic study based on RFID technology. International Journal of RF Technologies, 14(2), 107-124. https://doi.org/10.3233/RFT-230059.

13. He, X., Ma, Y., Li, T., Sun, Q., & Feng, Q. (2025). Real-time liquid level monitoring with low-cost uhf rfid sensors. IEEE sensors journal, 25(6), 10261-10271. https://doi.org/10.1109/JSEN.2025.3528128.

14. Hou, W., & Zhang, S. (2024). Assembly line balancing and optimal scheduling for flexible manufacturing workshop. Journal of Mechanical Science and Technology, 38(6), 2757–2772. https://doi.org/10.1007/s12206-024-2206-2.

15. Kumar, M. (2023). Integration of RFID strategic value attributes mechanism decision in apparel supply chain: fuzzy AHP-TOPSIS approach. Journal of Modelling in Management, 18(4), 1022–1063. https://doi.org/10.1108/JM2-11-2021-0283.

16. Li, K. (2023). Optimizing warehouse logistics scheduling strategy using soft computing and advanced machine learning techniques. Soft computing: A fusion of foundations, methodologies and applications, 27(23), 18077–18092. https://doi.org/10.1007/s00500-023-09269-4.

17. Maïzi, Y., & Bendavid, Y. (2023). Hybrid RFID-IoT simulation modeling approach for analyzing scrubs’ distribution solutions in operating rooms. Business Process Management Journal, 29(6), 1734–1761. https://doi.org/10.1108/BPMJ-12-2022-0658.

18. Pereira, E. S. S., Ordoñez, R. E. C., Beydoun, G., & Babar, A. (2024). Exploring the nexus of RFID and industry 4.0: Bibliometric analysis to investigate the strategic themes and thematic evolution. Journal of Industrial Engineering and Management, 17(1), 1–34. https://doi.org/10.3926/jiem.6235.

19. Pereira, E., Araújo, Í., Silva, L. F. V., Batista, M., Júnior, S., & Barboza, E., et al. (2023). RFID Technology for Animal Tracking: A Survey. IEEE Journal of Radio Frequency Identification, 7(1), 609–620. https://doi.org/10.1109/JRFID.2023.3334952.

20. Rajesh, V., & Rahuman, A. K. (2025). Flamingo lyrebird optimization‐based holistic approach for improving rfid‐wsn integrated network lifetime. International Journal of Communication Systems, 38(6), e70036.1-16. https://doi.org/10.1002/dac.70036.

21. Sheng, Y., Wang, J., Zhang, D., & Long, H. (2023). Research on Intelligent Engineering Management System Based on Rfid. Highlights in Science, Engineering and Technology, 71(3), 452–458. https://doi.org/10.54097/hset.v71i.14663.

22. Su, Z., Li, W., Li, J., & Cheng, B. (2022). Heterogeneous fleet vehicle scheduling problems for dynamic pickup and delivery problem with time windows in shared logistics platform: Formulation, instances and algorithms. International Journal of Systems Science: Operations & Logistics, 9(2), 199–223. https://doi.org/10.1080/23302674.2020.1865475.

23. Trebuna, P., Matiscsak, M., Kliment, M., & Pekarcikova, M. (2023). The usage of RFID robots in logistics process management. Acta logistica, 10(1), 89–93. https://doi.org/10.22306/al.v10i1.359.

24. Wang, D. M., Cai, J. H., Wu, J., Li, D. Z., Hu, J. G., & Zhong, Q. H. (2025). A 3 Kbits of Low-Cost, Low-Power EEPROM Integrated Into RFID Tag Integrated Circuits Available for Bio-Consumer Electronics. Consumer Electronics, IEEE Transactions on, 71(2), 5437-5445. https://doi.org/10.1109/TCE.2025.3564645.

25. Yuan, X., Zhu, J., Li, Y., Huang, H., & Wu, M. (2021). An enhanced genetic algorithm for unmanned aerial vehicle logistics scheduling. IET Communications, 15(10), 1402–1411. https://doi.org/10.1049/cmu2.12106.

26. Zhang, L. H., Tian, L., & Chang, L. Y. (2022). Equilibrium strategies of channel structure and RFID technology deployment in a supply chain with manufacturer encroachment. International Journal of Production Research, 60(6), 1890–1912. https://doi.org/10.1080/00207543.2021.1876943.

27. Zhang, Y. (2022). Logistics distribution scheduling model of supply chain based on genetic algorithm. Journal of Industrial and Production Engineering, 39(2), 83–88. https://doi.org/10.1080/21681015.2021.1958938.

28. Zhong, Z., Guo, Y., Zhang, J., & Yang, S. (2023). Energy-aware Integrated Scheduling for Container Terminals with Conflict-free AGVs. Journal of Systems Science and Systems Engineering, 32(4), 413–443. https://doi.org/10.1007/s11518-023-5563-y.