References

inform

Информатика

Informatics

1816-03012617-6963

UIIP NASB

10.37661/1816-0301-2022-19-4-94-110

inform-1223

Research Article

ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ

INFORMATION TECHNOLOGY

Модели и методы машинного обучения для решения задач оптимизации и прогнозирования работы морских портов

Machine learning models and methods for solving optimization and forecasting problems of the work of seaports

Лукашевич

М. Н.

Lukashevich

M. N.

Лукашевич Михаил Николаевич, аспирант, факультет прикладной математики и информатики

пр. Независимости, 4, Минск, 220050

Mikhail N. Lukashevich, Postgraduate Student, the Faculty of Applied Mathematics and Computer Science

av. Nezavisimosti, 4, Minsk, 220050

mikhail.n.lukashevich@gmail.com

Ковалев

М. Я.

Kovalyov

M. Y.

Ковалев Михаил Яковлевич, член-корреспондент НАН Беларуси

ул. Сурганова, 6, Минск, 220012

Mikhail Y. Kovalyov, Corresponding Member of the National Academy of Sciences of Belarus

st. Surganova, 6, Minsk, 220012

kovalyov_my@newman.bas-net.by

Белорусский государственный университетBelarusian State University

Объединенный институт проблем информатики Национальной академии наук БеларусиThe United Institute of Informatics Problems of the National Academy of Sciences of Belarus

2022

03112022

19494110

2022

Лукашевич М.Н., Ковалев М.Я.

Lukashevich M.N., Kovalyov M.Y.

Данная работа распространяется под лицензией Creative Commons Attribution 4.0.

This work is licensed under a Creative Commons Attribution 4.0 License.

https://inf.grid.by/jour/article/view/1223

За последнее десятилетие существенно улучшились методы машинного обучения и расширилась сфера их применения, которая дополнилась рядом операционных задач, возникающих в грузовых портах. Это связано с накоплением и возможностью использования имеющихся в грузовых портах больших объемов данных. Статья посвящена обзору литературы по моделям и методам машинного обучения и их применению к оптимизации портовых операций. Основное внимание уделено планированию и развитию портов, их безопасности и охране, водным и сухопутным портовым операциям.

Machine learning techniques have made significant advances and expanded application sphere over the past decade to include problems of port operations. This happened due to the growing amount of data available cargo ports. We review the literature on models and methods of machine learning and their application to optimization of port operations. A special attention is paid to the port planning and development a wide range of topics in port operations, including port planning and development, their safety and security, water and land port operations.

машинное обучениепрогнозирование работы портовпортовые операциианалитический обзоруправление международными перевозками

machine learningforecasting port forecastingport operationsanalytical reviewinternational transportation management

References1

Cheraghchi F., Abualhaol I., Falcon R., Abielmona R., Raahemi B., Petriu E. Big-data-enabled modelling and optimization of granular speed-based vessel schedule recovery problem. 2017 IEEE International Conference on Big Data (Big Data), Boston, USA, 11–14 December 2017, рр. 1786–1794. https://doi.org/10.1109/bigdata.2017.8258122

Mekkaoui S. E., Benabbou L., Berrado A. A systematic literature review of machine learning applications for port's operation. 5th International Conference on Logistics Operations Management (GOL), Rabat, Morocco, 28–30 October 2020, рр. 1–5. https://doi.org/10.1109/GOL49479.2020.9314756

Chen G., Govindan K., Yang Z. Managing truck arrivals with time windows to alleviate gate congestion at container terminals. International Journal of Production Economics, 2013, vol. 141, iss. 1, рр. 179–188. https://doi.org/10.1016/J.IJPE.2012.03.033

Dahal K., Galloway S., Hopkins I. Modelling, simulation and optimisation of port system management. International Journal of Agile Systems and Management, 2007, vol. 2, no. 1, pp. 92–108. https://doi.org/10.1504/ijasm.2007.015683

De A., Mamanduru V. K. R., Gunasekaran A., Subramanian N., Tiwari M. K. Composite particle algorithm for sustainable integrated dynamic ship routing and scheduling optimization. Computers and Industrial Engineering, 2016, vol. 96, рр. 201–215. https://doi.org/10.1016/j.cie.2016.04.002

Ghafoori A., Altiok T. A mixed integer programming framework for sonar placement to mitigate maritime security risk. Journal of Transportation Security, 2012, vol. 5, iss. 4, рр. 253–276. https://doi.org/10.1007/s12198-012-0095-6

John A., Paraskevadakis D., Bury A., Yang Z., Riahi R., Wang J. An integrated fuzzy risk assessment for seaport operations. Safety Science, 2014, vol. 68, рр. 180–194. https://doi.org/10.1016/j.ssci.2014.04.001

Li M. K., Yip T. L. Joint planning for yard storage space and home berths in container terminals. International Journal of Production Research, 2013, vol. 51, iss. 10, рр. 3143–3155. https://doi.org/10.1080/00207543.2012.760852

Lin J., Gao B., Zhang C. Simulation-based investment planning for Humen Port. Simulation Modelling Practice and Theory. 2014, vol. 40, рр. 161–175. https://doi.org/10.1016/j.simpat.2013.09.009

Said G. A. E.-N. A., El-Horbaty E.-S. M. An optimization methodology for container handling using genetic algorithm. Procedia Computer Science, 2015, vol. 65, рр. 662–671. https://doi.org/10.1016/j.procs.2015.09.010

Venturini G., Iris Ç., Kontovas C. A., Larsen A. The multi-port berth allocation problem with speed optimization and emission considerations. Transportation Research Part D: Transport and Environment, 2017, vol. 54, рр. 142–159. https://doi.org/10.1016/j.trd.2017.05.002

Zeinebou Z., Abdellatif B. Development of a model of decision support for optimization of physical flows in a container terminal. 2013 International Conference on Advanced Logistics and Transport, Tunisia, 29–31 May 2013, pp. 421–426. https://doi.org/10.1109/icadlt.2013.6568496

Awah P. C., Nam H., Kim S. Short term forecast of container throughput: new variables application for the Port of Douala. Journal of Marine Science and Engineering, 2021, vol. 9, iss. 7, р. 720. https://doi.org/10.3390/jmse9070720

Chan H. K., Xu S. Intelligent port data management systems to improve capability. 2017 International Conference on Service Systems and Service Management, Tokyo, Japan, 26–30 November 2017, рр. 1–3. https://doi.org/10.1109/icsssm.2017.7996283

Chan H. K., Xu S., Qi X. A comparison of time series methods for forecasting container throughput. International Journal of Logistics Research and Applications, 2019, vol. 22, iss. 3, рр. 294–303. https://doi.org/10.1080/13675567.2018.1525342

Cuong T. N., Kim H. S., You S. S., Nguyen D. A. Seaport throughput forecasting and post COVID-19 recovery policy by using effective decision-making strategy: A case study of Vietnam ports. Computers and Industrial Engineering, 2022, vol. 168, р. 108102. https://doi.org/10.1016/j.cie.2022.108102

Gamassa P. K. P., Chen Y. Application of several models for the forecasting of the container throughput of the Abidjan Port in Ivory Coast. International Journal of Engineering Research in Africa, 2017, vol. 28, рр. 157–168. https://doi.org/10.4028/www.scientific.net/JERA.28.157

Geng J., Li M. W., Dong Z. H., Liao Y. S. Port throughput forecasting by MARS-RSVR with chaotic simulated annealing particle swarm optimization algorithm. Neurocomputing, 2015, vol. 147, рр. 239–250. https://doi.org/10.1016/j.neucom.2014.06.070

Gosasang V., Chandraprakaikul W., Kiattisin S. A comparison of traditional and neural networks forecasting techniques for container throughput at Bangkok Port. The Asian Journal of Shipping and Logistics, 2011, vol. 27, no. 3, рр. 463–482. https://doi.org/10.1016/s2092-5212(11)80022-2

Gökkuş Ü., Yıldırım M. S., Aydin M. M. Estimation of container traffic at seaports by using several soft computing methods: a case of Turkish seaports. Discrete Dynamics in Nature and Society, 2017, vol. 2017, рр. 1–15. https://doi.org/10.1155/2017/2984853

Lam W. H. K., Ng P. L. P., Seabrooke W., Hui E. C. M. Forecasts and reliability analysis of port cargo throughput in Hong Kong. Journal of Urban Planning and Development, 2004, vol. 130, рр. 133–144. https://doi.org/10.1061/(asce)0733-9488(2004)130:3(133)

Milenkovic M., Milosavljevic N., Bojovic N., Val S. Container flow forecasting through neural networks based on metaheuristics. Operational Research, 2021, vol. 21, iss. 2, pр. 965–997. https://doi.org/10.1007/s12351-019-00477-1

Moscoso-Lopez J. A., Turias I. T., Come M. J., Ruiz-Aguilar J. J., Cerban M. Short-term forecasting of intermodal freight using ANNs and SVR: case of the Port of Algeciras Bay. Transportation Research Procedia, 2016, vol. 18, рр. 108–114. https://doi.org/10.1016/J.TRPRO.2016.12.015

Moscoso-Lopez J. A., Urda D., Ruiz-Aguilar J. J., Gonzalez-Enrique J., Turias I. J. A machine learningbased forecasting system of perishable cargo flow in maritime transport. Neurocomputing, 2020, vol. 452, рр. 487–497. https://doi.org/10.1016/j.neucom.2019.10.121

Alvarellos A., Figuero A., Carro H., Costas R., Sande J., Guerra A., Rabuñal J. Machine learning based moored ship movement prediction. Journal of Marine Science and Engineering, 2021, vol. 9, iss. 8, р. 800. https://doi.org/10.3390/jmse9080800

Atak Ü., Arslanoğlu Y. Machine learning methods for predicting marine port accidents: a case study in container terminal. Ships and Offshore Structures, 2021, рр. 1–8. https://doi.org/10.1080/17445302.2021.2003067

Cheng G., Wang S., Guo T., Han X., Cai G., Gao F., Dong J. Abnormal behavior detection for harbour operator safety under complex video surveillance scenes. 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), Harbin Institute of Technology (Shenzhen), China, 15–17 December 2017, рр. 324–328. https://doi.org/10.1109/spac.2017.8304298

Hoshino R., Coughtrey D., Sivaraja S., Volnyansky I., Auer S., Trichtchenko A. Applications and extensions of cost curves to marine container inspection. Annals of Operations Research, 2009, vol. 187, iss. 1, рр. 159–183. https://doi.org/10.1007/s10479-009-0669-2

Drummond C., Holte R. C. Cost curves: an improved method for visualizing classifier performance. Machine Learning, 2006, vol. 65, рр. 95–130. https://doi.org/10.1007/s10994-006-8199-5

Kim J. H., Kim J., Lee G., Park J. Machine learning-based models for accident prediction at a Korean container port. Sustainability, 2021, vol. 13, iss. 16, р. 9137. https://doi.org/10.3390/su13169137

Lee H. T., Lee J. S., Son W. J., Cho I. S. Development of machine learning strategy for predicting the risk range of ship's berthing velocity. Journal of Marine Science and Engineering, 2020, vol. 8, iss. 5, р. 376. https://doi.org/10.3390/jmse8050376

Ozturk U., Birbil S. I., Cicek K. Evaluating navigational risk of port approach manoeuvrings with expert assessments and machine learning. Ocean Engineering, 2019, vol. 192, р. 106558. https://doi.org/10.1016/j.oceaneng.2019.106558

Xiao Y., Wang G., Lin K. C., Qi G., Li K. X. The effectiveness of the New Inspection Regime for Port State Control: Application of the Tokyo MoU. Marine Policy, 2020, vol. 115, р. 103857. https://doi.org/10.1016/j.marpol.2020.103857

Yan R., Wang S., Peng C. An artificial intelligence model considering data imbalance for ship selection in port state control based on detention probabilities. Journal of Computational Science, 2021, vol. 48, р. 101257. https://doi.org/10.1016/j.jocs.2020.101257

Fotuhi F., Huynh N., Vidal J. M., Xie Y. Modeling yard crane operators as reinforcement learning agents. Research in Transportation Economics, 2013, vol. 42, iss. 1, рр. 3–12. https://doi.org/10.1016/j.retrec.2012.11.001

Gao Y., Chang D., Chen C. H., Fang T. Deep learning with long short-term memory recurrent neural network for daily container volumes of storage yard predictions in port. International Conference on Cyberworlds (CW), Singapore, 3–5 October 2018, рр. 427–430. https://doi.org/10.1109/cw.2018.00083

Gao Y., Chang D., Fang T., Fan Y. The daily container volumes prediction of storage yard in port with long short-term memory recurrent neural network. Journal of Advanced Transportation, 2019, vol. 2019, рр. 1–11. https://doi.org/10.1155/2019/5764602

Hottung A., Tanaka S., Tierney K. Deep learning assisted heuristic tree search for the container pre-marshalling problem. Computers and Operations Research, 2020, vol. 113, р. 104781. https://doi.org/10.1016/j.cor.2019.104781

Tierney K., Pacino D., Voß S. Solving the pre-marshalling problem to optimality with A* and IDA*. Flexible Services and Manufacturing Journal, 2016, vol. 29, iss. 2, рр. 223–259. https://doi.org/10.1007/s10696-016-9246-6

Kang J., Ryu K. R., Kim K. H. Deriving stacking strategies for export containers with uncertain weight information. Journal of Intelligent Manufacturing, 2006, vol. 17, iss. 4, рр. 399–410. https://doi.org/10.1007/s10845-005-0013-x

Kourounioti I., Polydoropoulou A., Tsiklidis C. Development of models predicting Dwell Time of import containers in port container terminals – an Artificial Neural Networks application. Transportation Research Procedia, 2016, vol. 14, рр. 243–252. https://doi.org/10.1016/j.trpro.2016.05.061

Moini N., Boile M., Theofanis S., Laventhal W. Estimating the determinant factors of container dwell times at seaports. Maritime Economics and Logistics, 2012, vol. 14, iss. 2, рр. 162–177. https://doi.org/10.1057/mel.2012.3

Saikia S., Verma R., Agarwal P., Shroff G., Vig L., Srinivasan A. Evolutionary RL for container loading. ESANN 2018 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Belgium, 25–27 April 2018. https://doi.org/10.48550/arXiv.1805.06664

Shen Y., Zhao N., Xia M., Du X. A Deep Q-Learning Network for ship stowage planning problem. Polish Maritime Research, 2017, vol. 24, no. s3, рр. 102–109. https://doi.org/10.1515/pomr-2017-0111

AbuAlhaol I., Falcon R., Abielmona R., Petriu E. Mining Port Congestion Indicators from Big AIS Data. The 2018 International Joint Conference on Neural Networks (IJCNN 2018), Brazil, 8–13 July 2018, рр. 1–8. https://doi.org/10.1109/ijcnn.2018.8489187

De Leon A. D., Lalla-Ruiz E., Melian-Batista B., Marcos Moreno-Vega J. A Machine Learning-based system for berth scheduling at bulk terminals. Expert Systems with Applications, 2017, vol. 87, рр. 170–182. https://doi.org/10.1016/j.eswa.2017.06.010

Fancello G., Pani C., Pisano M., Serra M., Zuddas P., Fadda P. Prediction of arrival times and human resources allocation for container terminal. Maritime Economics and Logistic, 2011, vol. 13, iss. 2, рр. 142–173. https://doi.org/10.1057/mel.2011.3

Kim S., Kim H., Park Y. Early detection of vessel delays using combined historical and real-time information. Journal of the Operational Research Society, 2017, vol. 68, iss. 2, рр. 182–191. https://doi.org/10.1057/s41274-016-0104-4

Sutrisnowati R. A., Bae H., Song M. Bayesian network construction from event log for lateness analysis in port logistics. Computers and Industrial Engineering, 2015, vol. 89, рр. 53–66. https://doi.org/10.1016/j.cie.2014.11.003

Verma R., Saikia S., Khadilkar H., Agarwal P., Shroff G., Srinivasan A. A reinforcement learning framework for container selection and ship load sequencing in ports. Proceedings of the Fourth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 4), Monreal, 13–17 May 2019, рр. 2250–2252.

Wang Y., Shi G., Sun X. A forecast model of the number of containers for containership voyage. Algorithms, 2018, vol. 11, no. 12, р. 193. https://doi.org/10.3390/a11120193

Yu J., Tang G., Song X., Yu X., Qi Y., Li D., Zhang Y. Ship arrival prediction and its value on daily container terminal operation. Ocean Engineering, 2018, vol. 157, рр. 73–86. https://doi.org/10.1016/j.oceaneng.2018.03.038

Al-Deek H. Which method is better for developing freight planning models at seaports-neural networks or multiple regression? Transportation Research Record: Journal of the Transportation Research Board, 2001, vol. 1763, iss. 1, рр. 90–97. https://doi.org/10.3141/1763-14

Chu C. H. Empirical method for predicting internal-external truck trips at a major port. Journal of Transportation Engineering, 2010, vol. 137, no. 7, рр. 496–508. https://doi.org/10.1061/(asce)te.1943-5436.0000233

Hill A., Bose J. W. A decision support system for improved resource planning and truck routing at logistic nodes. Information Technology and Management, 2017, vol. 18, iss. 3, рр. 241–151. https://doi.org/10.1007/s10799-016-0267-3

Huynh N., Hutson N. Mining the sources of delay for dray trucks at container terminals. Transportation Research Record: Journal of the Transportation Research Board, 2008, vol. 2066, iss. 1, рр. 41–49. https://doi.org/10.3141/2066-05

Jeon S. M., Kim K. H., Kopfer H. Routing automated guided vehicles in container terminals through the Q-learning technique. Logistics Research, 2010, vol. 3, iss. 1, рр. 19–27. https://doi.org/10.1007/s12159-010-0042-5

Pham Q., Huynh N., Xie Y. Estimating truck queuing time at marine terminal gates. Transportation Research Record: Journal of the Transportation Research Board, 2011, vol. 2222, iss. 1, рр. 45–53. https://doi.org/10.3141/2222-06

Sarvareddy P., Al-Deek H., Klodzinski J., Anagnostopoulos G. Evaluation of two modeling methods for generating heavy-truck trips at an intermodal facility by using vessel freight data. Transportation Research Record: Journal of the Transportation Research Board, 2005, vol. 1906, iss. 1, рр. 113–120. https://doi.org/10.1177/0361198105190600114

Van Riessen B., Negenborn R. R., Dekker R. Real-time container transport planning with decision trees based on offline obtained optimal solutions. Decision Support Systems, 2016, vol. 89, pp. 1–16. https://doi.org/10.1016/j.dss.2016.06.004

Zeng Q., Yang Z. Z., Lai L. Models and algorithms for multicrane oriented scheduling method in container terminals. Transport Policy, 2009, vol. 16, iss. 5, рр. 271–278. https://doi.org/10.1016/J.TRANPOL.2009.08.006

The authors declare that there are no conflicts of interest present.