Increasing competition in the container shipping sector has meant thatterminals are having to equip themselves with increasingly accurate analytical andgovernance tools. A transhipment terminal is an extremely complex system in terms of bothorganisation and management. Added to the uncertainty surrounding ships’ arrival time inport and the costs resulting from over-underestimation of resources is the large number ofconstraints and variables involved in port activities. Predicting ships delays in advancemeans that the relative demand for each shift can be determined with greater accuracy, andthe basic resources then allocated to satisfy that demand. To this end, in this article wepropose two algorithms: a dynamic learning predictive algorithm based on neural networksand an optimisation algorithm for resource allocation. The use of these two algorithmspermits on the one hand to reduce the uncertainty interval surrounding ships’ arrival inport, ensuring that human resources can be planned around just two shifts. On the otherhand, operators can be optimally allocated for the entire workday, taking into accountactual demand and operations of the terminal. Moreover, as these algorithms are based ongeneral variables they can be applied to any transhipment terminal. Future integration ofthe two models within a broader decision support system will provide an important supporttool for planners for fast, flexible planning of the terminal’s operations management.
|Numero di pagine||32|
|Rivista||MARITIME ECONOMICS & LOGISTICS|
|Stato di pubblicazione||Published - 2011|
All Science Journal Classification (ASJC) codes
- Economics, Econometrics and Finance (miscellaneous)