[ICACE2022] Prediction of container vessel waiting time in Busan port using LSTM neural network
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study proposes a long short-term memory neural network model to predict the waiting time of container vessels at Busan Port. Based on Port Management Information System (Port-MIS) data, the vessel waiting time and vessel service time of con-tainer vessels in Busan Port were extracted from the vessel calling status (VCS) between January 2001 and August 2022. The method and procedures for calculating the vessel waiting time and vessel service time using the time stamp, call sign, number of arrivals, vessel type, navigation status, and facility code are described for ongoing measurements. Additionally, a multivariate long short-term memory model was applied to predict the future vessel waiting time with the vessel service time, number of waiting vessels, and container throughput as the input features. Predictions were made multiple times with different window sizes, and the mean square error, mean absolute error, and root mean square error were used to assess the performance of the model. The results prove the feasibility of using the long short-term memory model for predicting the vessel waiting time. The computation method and prediction model of this study provide significant implications and support shipping market participants and port authorities in making more informed decisions regarding the utilization of port facilities and the upcoming port congestion status.
Abstract
This study proposes a long short-term memory neural network model to predict the waiting time of container vessels at Busan Port. Based on Port Management Information System (Port-MIS) data, the vessel waiting time and vessel service time of con-tainer vessels in Busan Port were extracted from the vessel calling status (VCS) between January 2001 and August 2022. The method and procedures for calculating the vessel waiting time and vessel service time using the time stamp, call sign, number of arrivals, vessel type, navigation status, and facility code are described for ongoing measurements. Additionally, a multivariate long short-term memory model was applied to predict the future vessel waiting time with the vessel service time, number of waiting vessels, and container throughput as the input features. Predictions were made multiple times with different window sizes, and the mean square error, mean absolute error, and root mean square error were used to assess the performance of the model. The results prove the feasibility of using the long short-term memory model for predicting the vessel waiting time. The computation method and prediction model of this study provide significant implications and support shipping market participants and port authorities in making more informed decisions regarding the utilization of port facilities and the upcoming port congestion status.
참고문헌 (23)
- "Trade-to-GDP Ratio"[URL]
- 이민규, "항만 서비스 혁신 관점에서의 선박 재항 시간의 결정요인 분석", 한국혁신학회지, 7(1), pp.51~69 (2012), 한국혁신학회[DOI]
- G. -T. Yeo, "The hierarchical analysis of perceived competitiveness : An application to Korean con-tainer ports", Journal of the Eastern Asia Society for Trans-portation Studies, 6, pp.866~880 (2005)
- 김은수, "국내 항만의 선박 대기율 실증 분석 연구", 한국항해항만학회지, 40(1), pp.35~41 (2016), 한국항해항만학회[DOI]
- 이정훈, "컨테이너 터미널의 이론적 대기율과 실제 대기율 비교에 관한 연구: 부산항 신항 A 터미널을 대상으로", 한국항만경제학회지, 34(2), pp.69~82 (2018), 한국항만경제학회[DOI]
- "Port-MIS"[URL]
- 김민진, "항만운영정보시스템(Port-MIS) 서비스 품질 평가에 관한 연구", 한국항만경제학회지, 29(2), pp.211~238 (2013), 한국항만경제학회
- "Current Status of Busan Port"[URL]
- "Overall Status of Port Facilities in Busan Port"[URL]
- J. -Y. Oh, "Analysis of Port-MIS data for pre-diction of anchorage waiting time", Proceedings of the 2020 KAOSTS Fall Conference, pp.3~4 (2020)
- S. Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- 김원열, "A study on oil-film detection technique using IR-UWB radar-based Bi-LST", 한국마린엔지니어링학회지, 42(10), pp.843~850 (2018), 한국마린엔지니어링학회[DOI]
- 조민우, "항만 터미널의 컨테이너 트럭 턴타임 예측 시스템 구축", 물류학회지, 32(4), pp.105~114 (2022), 한국물류학회
- Z. Cui, "Stacked bidi-rectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing val-ues", Transportation Research Part C: Emerging Technolo-gies, 118, pp.102674~ (2020)
- H. Lütkepohl, "New Introduction to Multiple Time Series Analysis" (2006), Springer
- J. Franzkeit, "Investigation of vessel waiting times using AIS data", Proceedings of International Conference on Dynamics in Logistics, pp.70~78 (2020)
- W. Peng, "A deep learning approach for port congestion estimation and pre-diction", Maritime Policy & Management, pp.1~26 (2022)
- S. V. Belavadi, "Air quality forecasting using LSTM RNN and wireless sensor networks", Procedia Computer Science, 170, pp.241~248 (2020)
- D. -H. Shin, "Prediction of traffic congestion based on LSTM through correction of missing temporal and spatial data", IEEE Access, 8, pp.150784~150796 (2020)
- J. W. Tukey, "Exploratory Data Analysis" (1977), Addison-Wesley
- R. A. Jacobs, "Increased rates of convergence through learning rate adaption", Neural Networks, 1(4), pp.295~307 (1988)
- F. U. M. Ullah, "Short-term prediction of residential power energy consumption via CNN and multi-layer bi-directional LSTM networks", IEEE Access, 8, pp.123369~123380 (2020)
- F. Jiang, "Forecasting port container throughput with deep learning approach", Proceedings of the 5th International Conference on Computer Science and Application Engineering, pp.1~4 (2021)