Managing vessel arrival uncertainty in container terminals: a machine learning approach

摘要

A container terminal is a complex system where a broad range of operations areudcarried out involving a wide array of resources that need to interact over a 24 hourudoperating cycle. Since the various activities are mutually related to each other, there isuda need not only to maximise the efficiency of each one, but also to ensure properudcoordination, hence to solve integrated decision-making problems. Several factors canudaffect the quality of the services provided and the overall efficiency. Vessel arrivaluduncertainty further complicates the task of the planners and, as a result, of theudeffectiveness of the planning itself, in particular at the operational level. Each arrivaludproduces high peak loads for other terminal activities, as well as for the supportingudarrival activities (pilotage, towage, etc.) and hinterland transportation (waiting,udcongestion etc.). Deviating arrivals only worsen this peak load.udOn a daily level, the actual time of arrival of the vessels often deviates from theudscheduled time. Despite contractual obligations to notify the Estimated Time ofudArrival (ETA) at least 24 hours before the arrival, ship operators often have to adaptudand update the latest ETA due to unexpected circumstances. This aspect results in audlast-minute change of plans in terminal operations resulting in higher costs. In fact, theudability to predict the actual time of a vessel’s arrival in a port 24 hours in advance isudfundamental for the related planning activities for which the decision-makingudprocesses need to be constantly adapted and updated. Moreover, disruptions inudcontainer flows and operations caused by vessel arrival uncertainty can have cascadeudeffects within the overall supply chain and network within which the port is part.udAlthough vessel arrival uncertainty in ports is a well-known problem for the scientificudcommunity, the literature review highlights that in the maritime sector the specificudinstruments for dealing with this problem are extremely limited.udThe absence of a reference model that specifies the relationship between vessel arrivaluduncertainty and the involved variables resulted in the application of a specific machineudlearning approach within the Knowledge Discovery in Database process. ThisudVudapproach, that abandons all prior assumptions about data distribution shape, is basedudon the self-learning concept according to which the relation between an outcomeudvariable Y and the set of predictors X is directly identified from the historical collecteduddata.udThe approach has been validated thanks to two different case studies: the containerudterminal of Cagliari, located in the Mediterranean basin, and one of the main containerudterminals of Antwerp, located at the North Sea.udDepending on the framework and planning purposes several estimates can provideuduseful information on vessel arrivals. Sometimes, it can be useful for planners to inferuda quantitative estimate of the delay/advance in minutes, sometimes it may be useful toudhave a qualitative estimate, even only knowing whether or not an incoming vessel isudlikely to arrive before or after the scheduled ETA. For this reason a two-stepudinstrument is proposed is made up of two different modules.udThe fitted algorithmic models used to obtain predictions are Logistic Regression,udCART (Classification and Regression Trees) and Random Forest. All the proposed models are able to learn from experience, following the well-known Data Mining paradigm “learning from data”. From a practical point of view, the probability, associated to the continuous estimation, of specifically identifying the work-shift of the incoming vessel is calculated. In all predictions Random Forest algorithms still show the best performance. This aspect can help planners, in the daily strategy decision making process, in order to improve the use of the human, mechanical and spatial resources required for handling operations. This could maximise terminal efficiency and minimise terminal costs, hence improving terminal competitiveness. Moreover, the interpretation of the discovered knowledge, made it possible to evaluateudthe most discriminating variables of the analysis, even thanks to graphical visualisation of the Importance-plots.ud