As international regulations for commercial ships regarding environmental pollution and global warming are being reinforced, worldwide efforts are growing to reduce the fuel consumption of ships; this is directly related to the emissions of environmental pollutants and greenhouse gases. A common method to reduce the fuel consumption of ships is to find a ship route that consumes less fuel. In many existing ship route optimization studies, the desired ship routes are calculated using a single objective optimization algorithm such as A * to minimize the path length, travel time, or fuel consumption. However, it is practically more important to reach the destination no later than the alloted time slot at a port even under weather uncertainties. In this study, a multi-objective optimization algorithm is employed to calculate the Pareto set with two objective functions: the fuel consumption and the expected time of arrival. Subsequently, using the Pareto set, the uncertainty of the arrival time and the probability that the ship will arrive within the specified time are estimated. Finally, the route to reach the port on time is determined with more certainty while minimizing fuel consumption. In order to verify the validity of the proposed method, a set of simulations were performed, and their results are discussed.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Ship Route Optimization Considering On-Time Arrival Probability Under Environmental Uncertainty


    Beteiligte:
    Yoo, Byunghyun (Autor:in) / Kim, Jinwhan (Autor:in)


    Erscheinungsdatum :

    01.05.2018


    Format / Umfang :

    1125162 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Multi-Armed Bandit On-Time Arrival Algorithms for Sequential Reliable Route Selection under Uncertainty

    Zhou, Jinkai / Lai, Xuebo / Chow, Joseph Y. J. | Transportation Research Record | 2019