Skip to content
KPI Science News
ISSN 2617-5509 · e‑ISSN 2663-7472 Open Access · CC BY 4.0
Vol. 138 · Issue 1 · 2025 Apr 24, 2025 article

Fleet management algorithm for enhancing environmental friendliness of maritime delivery

AR
Andriy Romanov Corresponding Odesa National Maritime University, department of Technical Cybernetics and Information Technology named after prof. R.V. Merkt, Ukraine Ukraine
PublishedApr 24, 2025
PDF (Ukrainian)
KPISN 1 VOL 138 · 1
VOL 138 · ISS 1 · 2025 View issue

Abstract

Background . Maritime cargo delivery accumulates over 80% of international transport operations, providing a cost-effective method for global trade, particularly vital for developing countries. However, maritime transportation is heavily dependent on fossil fuels, which results in significant emissions of carbon dioxide (CO 2 ) and creates environmental problems for water resources. To address these issues, this study proposes a solution to optimize maritime delivery route planning projects, and reduce fuel consumption and CO 2 emissions. Objective. The objective is to develop an algorithm for planning delivery routes at optimal vessel speed, consisting of a genetic algorithm and a speed optimization step, to reduce fuel consumption and CO 2 emissions during maritime transportation. In addition, the results will be validated and the efficiency of the developed algorithm will be compared with a standard genetic algorithm without a speed optimization step. Methods. This article proposes an implementation of an additional step of vessel speed optimization into the algorithm for calculating delivery routes, which can significantly reduce fuel consumption and CO 2 emissions without increasing the complexity of the algorithm itself. The route is computed by solving the vehicle routing problem. Results. The study demonstrates that the application of the speed optimization step in the algorithm for planning delivery routes significantly reduces the volumes of fuel consumption and CO 2 emissions. Comparison of the experimental results showed that the genetic algorithm with a speed optimization step outperforms the standard genetic algorithm in terms of the volumes of fuel used and CO 2 emissions. Detailed analysis of various combinations of fleet composition emphasizes the need to balance the capacity of vessels to achieve maximum efficiency of cargo delivery. While adding more feeders initially reduces overall fuel consumption, overloading the fleet with underutilized vessels can lead to inefficiencies and increased operational costs. The study also considers alternative approaches such as increasing capacity and reallocating vessels among routes, highlighting their impact on fuel consumption and CO 2 emissions. Conclusions. The study proposes an improved algorithm for constructing maritime cargo delivery routes using a genetic algorithm with a speed optimization step. Such an algorithm ensures effective management of maritime delivery route planning projects, while significantly reducing fuel consumption and CO 2 emissions into the environment. Also, optimal control of the fleet composition ensures the reduction of CO 2 emissions due to the efficient use of each vessel.

Keywords

#maritime cargo delivery #genetic algorithm #route optimization #fuel consumption and CO2 emissions #environmental impact #feeder speed optimization #fleet management

References

  1. UNCTAD. Review of Maritime Transport, 2024. URL: https://unctad.org/topic/transport-and-trade-logistics/review-of-maritime-transport
  2. Walker, T. R., Adebambo, O., Del Aguila Feijoo, M. C., Elhaimer, E., Hossain, T., Edwards, S. J., Morrison, C. E., Romo, J., Sharma, N., Taylor, S., & Zomorodi, S. (2019). Chapter 27 — Environmental Effects of Marine Transportation. In World Seas: An Environmental Evaluation (pp. 505–530). Academic Press, Cambridge, Massachusetts, USA. https://doi.org/10.1016/B978-0-12-805052-1.00030-9
  3. Li, W., Pundt, R., & Miller-Hooks, E. (2021). An updatable and comprehensive global cargo maritime network and strategic seaborne cargo routing model for global containerized and bulk vessel flow estimation. Maritime Transport Research, 2, 100038. https://doi.org/10.1016/j.martra.2021.100038
  4. UNCTAD. Review of Maritime Transport 2023, 2024. URL: https://unctad.org/system/files/official-document/rmt2023_en.pdf
  5. Meyer, J., Stahlbock, R. and Voss, S. (2012). Slow Steaming in Container Shipping. Proceedings of the 45th Hawaii International Conference on System Sciences (pp. 1306-1314). doi: https://doi.org/10.1109/HICSS.2012.529
  6. Bushuyeva, N., Ivko, A., Romanov, A., Malaksiano, M. and Romanuke, V. (2024). Genetic Algorithm for Maritime Route Planning Projects with Improved Constraints. In Proceedings of the 5th International Workshop IT Project Management (ITPM 2024) (pp. 126–140). Bratislava, Slovakia, May 22, 2024.
  7. Krstev, D., Pop-Andonov, G., Krstev, A., Djidrov, M., Krstev, B., & Pavlov, S. (2014). The Multiple Travelling Salesman Problem and Vehicle Routing Problem for Different Domestic Drinks. International Scientific Journal "Machines. Technologies. Materials," 8(4), 17–18.
  8. Hertz, A., & Widmer, M. (2003). Guidelines for the use of meta-heuristics in combinatorial optimization. European Journal of Operational Research, 151(2), 247–252. https://doi.org/10.1016/S0377-2217(02)00823-8
  9. Colorni, A., Dorigo, M., Maffioli, F., Maniezzo, V., Righini, G., & Trubian, M. (1996). Heuristics from nature for hard combinatorial optimization problems. International Transactions in Operational Research, 3(1), 1–21. https://doi.org/10.1016/0969-6016(96)00004-4
  10. Chambers, L. D. (2000). The Practical Handbook of Genetic Algorithms. Chapman and Hall/CRC.
  11. Haupt, R. L., & Haupt, S. E. (2003). Practical Genetic Algorithms. John Wiley & Sons. https://doi.org/10.1002/0471671746
  12. V Romanuke, V. V., Romanov, A. Y., & Malaksiano, M. O. (2023). A genetic algorithm improvement by tour constraint violation penalty discount for maritime cargo delivery. System Research and Information Technologies, 2, 104–126. https://doi.org/10.20535/srit.2308-8893.2023.2.08
  13. Romanuke, V. V., Romanov, A. Y., & Malaksiano, M. O. (2022). Pseudorandom number generator influence on the genetic algorithm performance to minimize maritime cargo delivery route length. Scientific Journal of Maritime Research, 36, 249–262. https://doi.org/10.31217/p.36.2.9
  14. Romanuke, V. V., Romanov, A. Y., & Malaksiano, M. O. (2022). Crossover operators in a genetic algorithm for maritime cargo delivery optimization. Journal of ETA Maritime Science, 10(4), 223–236. https://doi.org/10.4274/jems.2022.80958
  15. Gülmez, B., Emmerich, M., & Fan, Y. (2024). Multi-objective Optimization for Green Delivery Routing Problems with Flexible Time Windows. Applied Artificial Intelligence, 38(1). https://doi.org/10.1080/08839514.2024.2325302
  16. Yüksel, O. and Köseoğlu, B. (2022) “Regression Modelling Estimation of Marine Diesel Generator Fuel Consumption and Emissions”, Transactions on Maritime Science. Split, Croatia, 11(1), pp. 79–94. doi: 10.7225/toms.v11.n01.w08.
§ 06 — Related

Similar articles in this journal

Related peer-reviewed studies published in this journal.
View all issues

MODIFICATION OF THE SEPARABLE PHYSICS-INFORMED NEURAL NETWORK METHOD FOR THE APPROXIMATE SOLUTION OF A MIXED PROBLEM FOR THE HEAT CONDUCTION EQUATION IN AN ELLIPTICAL DOMAIN

Valerii Los, Oleksandr Riakhin

Background. Parabolic differential equations are mathematical models in engineering designed to study wide range of applied models. This necessitates the development of…

#heat conduction equation #mixed parabolic problem #elliptical domain #physics-informed neural network
10.20535/kpisn.2026.3.367316

Similar Articles

1-10 of 115

You may also start an advanced similarity search for this article.