Just in Time Bunkering Operations: AI model for bunkering operations optimization.

24 October, 2023

Summary:

At present, bunkering operations in ports are not exempt from certain congestion problems, which can lead, in some cases, to delays in the start of these services to the vessel. Similarly, factors such as the lack of global visibility, coordination and real-time operational awareness of these operations could be improved. This would result in reduced waiting times and unnecessary fuel consumption by ships and bunkering barges and, consequently, lower GHG emissions in the port sector, as well as avoiding possible cost overruns and operational risks.

In this context, the Port Authority of the Bay of Algeciras (APBA) has explored through the proof of concept (PoC), called “JIT Bunkering Operations”, the development of a digital tool for the optimization of bunkering operations and the promotion of Just-in-Time ship arrivals.

The project has been developed in collaboration with Navozyme, a technology scale-up specialized in the development of deep-tech enabled digital solutions for the maritime sector, especially with blockchain technology and artificial intelligence.

Specifically, the scope of the proof of concept has consisted in the development of a prototype of a digital planning and decision support tool, based on an optimization model combined with artificial intelligence predictive analytics and machine learning techniques, to optimize bunkering operations at anchorage D of the Port of Algeciras.

The optimization model developed allows to obtain:

1. The prediction of the earliest possible availability of barges to attend the next operation according to the possible pre-refueling requirements.
2. A prediction of the possible arrival time (ETA) of the next vessel calls.
3. The estimation of the earliest possible time of completion of bunkering operations at anchorage.
4. Through the combination of the above estimates generate an optimal service window, including a recommendation of the vessel’s time of arrival at anchorage (RTA) and the start of service (RTS).

The ultimate goal is to minimize the waiting and idle times of vessels approaching the port by assigning them, on the one hand, an available bunkering barge, an anchorage and, on the other hand, an optimal operating window. In such a way that, when the vessels reach the designated anchorage area maintaining an optimum speed, they are guaranteed both the availability of bunkering services and an anchorage berth.

Likewise, there will be a reduction in the emissions generated by optimizing both the navigation speeds of the vessels towards the Port and the movements of the service providers.

The project’s innovation:

• Development of predictive and optimization models, based on artificial intelligence, to assist and improve decision making related to the management of anchorage bunkering operations.
• Development of prescriptive functionalities to improve the optimization of operations based on the use of a vessel port arrival recommendation (RTA) and barge service recommendation (RTS).
• Holistic and synchronous optimization of bunkering operations from the point of view of the service provider and the service receiver.

The project’s product:

• Prototype of a bunkering operations optimization model that allows to holistically manage the services to the vessel, determining an optimal service window and analyzing the impact of the actual development of the planned operations.

Usability/applicability:

• The future product or decision support tool (based on the validated prototype) would be very useful for the operational management of bunkering operations, increasing the overall efficiency of the process through improved planning and coordination between the agents involved.
• On the other hand, this tool could be extended to the rest of the ship services (provisioning, supplies, etc.) provided in the Port of Algeciras, optimizing such port operations and improving the value proposition offered.