Decision Support for Energy Efficiency Operations of Double Ended Ferry

Abstract

A year long navigation data was available for the double ended ROPAX ship "Uraniborg" owned by the company Rensiery Ventrafiken AB. Exploratory data analysis shows that allocating most of the engine’s load on the stern-most engine has potential for energy savings. Furthermore, a full black box machine learning XG Boost model-based simulator was built in order to forecast the total fuel consumption for a trip, given the meteocean conditions and some engine-related initial conditions (IC), on the assumption that the speed overground and the route remains the same. The simulator acts as a Decision Support System that allows an expert operator to make decisions on how to allocate the Power on the ship for a given trip, as well as to improve the Engine Speed operation of either engine.