Ship sailing speed optimization considering dynamic meteorological conditions

Abstract

Sailing speed optimization is a cost-effective strategy to improve ship energy efficiency and a viable way to fulfill emission reduction requirements. This study develops a novel ship sailing speed optimization method that considers dynamic meteorological conditions. We first develop an artificial neural network model for vessel fuel consumption rate (FCR) prediction based on a fusion dataset of ship noon reports and public meteorological data. Then, based on the predicted FCRs, the method repeatedly formulates a multistage graph based on the most recent forecasts, and optimal speeds for the remaining voyage are obtained until the vessel reaches the destination port. The computational efficiency of the optimization process is enhanced by progressively removing nodes without connections to successor nodes, starting from the penultimate stage. We examine the proposed method on two 11-day voyages of a dry bulk carrier. Results show that the proposed method demonstrates significant reductions in fuel consumption by 5.35% compared with a constant sailing speed scheme and by 7.34% compared with a static speed optimization model. In addition, the proposed model achieves similar fuel savings to those achieved by speed optimization based on actual meteorological conditions, enabling shipping companies to optimize ship sailing speeds in the absence of actual meteorological conditions. The proposed method can be applied to various types of vessels due to its flexibility and adaptability, making it a valuable tool for the shipping industry to reduce greenhouse gas (GHG) emissions, thereby supporting the International Maritime Organization (IMO)’s goal of reaching net-zero GHG emissions by around 2050.