Journal of Navigation and Port Research (한국항해항만학회지)

Korean Institute of Navigation and Port Research (한국항해항만학회)
권호 표지
DOI QR코드

DOI QR Code

Prediciton Model for External Truck Turnaround Time in Container Terminal

컨테이너 터미널 내 반출입 차량 체류시간 예측 모형

  • Yeong-Il Kim (KMI-KMOU Cooperation Course, National Korea Maritime and Ocean University) ;
  • Jae-Young Shin (Department of Logistics Engineering, National Korea Maritime and Ocean University)
  • 김영일 (국립한국해양대학교 KMI-KMOU 학연협동과정) ;
  • 신재영 (국립한국해양대학교 물류시스템학과)
  • Received : 2024.01.08
  • Accepted : 2024.02.13
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

Following the COVID-19 pandemic, congestion within container terminals has led to a significant increase in waiting time and turnaround time for external trucks, resulting in a severe inefficiency in gate-in and gate-out operations. In response, port authorities have implemented a Vehicle Booking System (VBS) for external trucks. It is currently in a pilot operation. However, due to issues such as information sharing among stakeholders and lukewarm participation from container transport entities, its improvement effects are not pronounced. Therefore, this study proposed a deep learning-based predictive model for external trucks turnaround time as a foundational dataset for addressing problems of waiting time for external trucks' turnaround time. We experimented with the presented predictive model using actual operational data from a container terminal, verifying its predictive accuracy by comparing it with real data. Results confirmed that the proposed predictive model exhibited a high level of accuracy in its predictions.

코로나 팬데믹 이후 컨테이너 터미널 내 혼잡도 증가에 따라 반출입 차량 작업 대기 및 체류시간이 급증하여 반출입 작업 비효율이 극심한 실정이다. 이에 항만 당국은 반출입예약시스템(Vehicle Booking System; VBS)을 구축하여 시범운영 중에 있으나 이해관계자 간 정보공유 문제 및 컨테이너 운송 주체의 미온적 참여 등으로 인해 개선효과가 뚜렷하지 않다. 따라서 본 연구에서는 반출입 차량의 작업 대기 및 체류시간 문제의 해결을 위한 기초자료로써, 딥러닝 기반의 반출입 차량 체류시간 예측 모형을 제시하였다. 실제 컨테이너 터미널의 반출입 운영 데이터를 통해 제시한 예측 모형을 실험하고 실제 데이터와 비교하여 예측 정확도를 검증한 결과 제시한 예측 모형이 높은 예측 정확도를 보이는 것을 확인하였다.

Keywords

Acknowledgement

본 논문은 2023년도 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 지자체-대학 협력기반 지역혁신 사업의 결과입니다.(2023RIS-007)

References

  1. Al-Deek, H.(2001), "Which Method Is Better for Developing Freight Planning Models at Seaports - Neural Networks or Multiple Regression", In Transportation Research Record: Journal of the Transportation Research Board, No. 1763, pp. 90-97.
  2. Al-Deek, H.(2002), "Use of Vessel Freight Data to Forecast Heavy Truck Movements at Seaports", In Transportation Research Record: Journal of the Transportation Research Board, No. 1804, pp. 217-224.
  3. Al-Deek, H., Johnson, G., Mohamed, A. and El-Maghraby, A.(2000), "Truck Trip Generation Models for Seaports with Container and Trailer Opertaion", In Transportation Research Record: Journal of the Transportation Research Board, No. 1719, pp. 1-9.
  4. Cho, M. W., Kim, T. Y. and Lee, B. W.(2022), "Turn-time Prediction System Implementation of Container Trucks at the Port Terminal", Korea Logistics Review, Vol. 32, No. 4, pp. 105-114.
  5. Kim, G. S.(2021), "Estimation on Storage Yard Occupancy Ratio of Container Terminal : A Case of Busan New Port Container Terminal", Journal of Korean Navigation and Port Research, Vol. 45, No. 3, pp. 148-154.
  6. Kim, J. H., Kim, J. S. and Lee, G. W.(2019), "A Study on Predicting Truck Arrivals at Busan Container Terminals in Korea", Journal of Maritime Business, Vol. 44, pp. 97-111.
  7. Kim, J. S., Kim, J. H, Shin, H. J and Lee, G. W.(2020), "Prediction of Truck Arrivals at Container Terminals based on LSTM Network", Korean Society of Transportation, Proceedings of the KOR-KST Conference, pp. 240-241.
  8. Kim, S. H., Kim, J. R., Cho, H. J. and Lim, C. H.(2019), "A Study on the Prediction of Traffic Volume by Time of Vehicles Entering and Exiting Port Container Terminal Using Machine Learning", Korean Institute of Industrial Engineers, 2019 Fall Conference of Korean Institute of Industrial Engineers, pp. 1412-1417.
  9. Kim, Y. I., Shin, J. Y and Park, H. J.(2022), "A Study on the Prediction of Gate In-Out Truck Waiting Time in the Container Terminal", Journal of Korean Navigation and Port Research, Vol. 46, No. 4, pp. 344-350.
  10. Korea Maritime Institute(KMI)(2023), "Pricing Model for Vehicle Booking Systems in Container Terminals", p. 167.
  11. Lee, S. J.(2011), "A Study on the Improvement of the Gate In-out Operation in the Container Terminals", Master Thesis of Korea Maritime and Ocean University.
  12. Li, N., Sheng, H., Wang, P., Jia, Y., Yang, Z. and Jin, Z.(2023), "Modeling Categorized Truck Arrivals at Ports: Big Data for Traffic Prediction", IEEE Transactions on Intelligent Transportation Systems, Vol.24, No.3, pp. 2772-2778. https://doi.org/10.1109/TITS.2022.3219882
  13. Ramachandran, P., Zoph, B. and V.Le, Q.(2017), "Swish - A Self-Gated Activation Function", arXiv preprint arXiv:1710.05941
  14. Reimers, N. and Gurevych, I.(2017), "Optimal Hyper-Parameters for Deep Lstm-Networks for Sequence Labeling Tasks", arXiv preprint arXiv:1707.06799.
  15. Xie, Y. and Huynh, N.(2010), "Kernel-Based Machine Learning Models for Predicting Daily Truck Volume at Seaport Terminals", Journal of Transportation Engineering, Vol. 136, No. 12, pp. 1145-1152.