An Isochrone-Based Predictive Optimization for Efficient Ship Voyage Planning and Execution

Abstract

A voyage optimization algorithm is an essential component in a ship's routing concerning safety, energy efficiency, arrival punctuality, etc. In this study, predictive optimization is integrated with an Isochrone-based voyage optimization algorithm for energy-efficient sailing. Different waypoints generation and grid partition strategies in search spaces are proposed to achieve smooth convergence toward the destination, and costs ahead of the current sailing time stages are estimated in the cost function to avoid the local suboptimization. Based on these measures, this paper introduces the Isochrone-based predictive optimization (IPO) method that can achieve enhanced and robust performance in real-time multi-objective voyage optimization. The unrealistic routes with abrupt turns that occur in the traditional Isochrone and graph search methods are avoided. The IPO method can suggest energy-efficient routes in diverse sailing environments, while complying with punctuality requirements in voyage planning. Meanwhile, it requires a few computational resources that enable online and real-time adjustment during voyage execution, adapting to dynamic sailing environments. Its efficiency and effectiveness are demonstrated by six case study voyages from a chemical tanker with full-scale measurements, and further compared with other widely used voyage optimization methods. The results show that the proposed method can provide smooth routes with subtle turns with 5% fuel reduction on average for all case voyages, with around 40 seconds runtime.