Optimization of Energy Efficiency for Ocean-Going Vessels based on Big Data Analysis

Abstract

With the ongoing advancement of the International Maritime Organization (IMO) greenhouse gas reduction strategy, energy efficiency management for ocean-going vessels has become a pivotal issue in the shipping industry's green and low-carbon transition. This paper systematically reviews the regulatory frameworks governing vessel energy efficiency management, with particular emphasis on the Energy Efficiency Design Index (EEDI), the Energy Efficiency Existing Ship Index (EEXI), the Carbon Intensity Indicator (CII), and the Ship Energy Efficiency Management Plan (SEEMP). Concurrently, the current applications of big data collection and processing technologies in maritime energy efficiency are critically examined. Building upon these foundational insights, we develop a comprehensive big data-driven energy efficiency optimization model framework that integrates a multi-dimensional energy performance indicator system, advanced data mining and machine learning methodologies, as well as speed optimization strategies and weather-based route selection algorithms. Extensive case studies are conducted to demonstrate the effectiveness of several predictive models, including back-propagation (BP) neural networks, random forests, and long short-term memory (LSTM) networks, in forecasting vessel fuel consumption with high accuracy. Notably, the multi-source data fusion model achieves a coefficient of determination (R²) of 0.9431, while the genetic algorithm-optimized LSTM (GA-LSTM) model exhibits a prediction error of merely 0.29 percent. The research conclusively indicates that big data-powered energy efficiency optimization approaches can significantly reduce vessel fuel consumption and carbon emissions, thereby providing robust scientific support and actionable decision-making tools for sustainable maritime operations in the era of digital transformation.