Smart Shipping Route Optimization for Fuel Efficiency Using Big Data Analytics

Abstract

This research aims to optimize shipping routes by applying big data analytics to improve fuel efficiency. By leveraging real-time and historical data, the study identified the most efficient routes to minimize fuel consumption without sacrificing operational effectiveness. Based on maritime logistics theory, big data analytics, and fuel efficiency, this research combines route optimization models, weather forecasts, and ship performance analysis to support navigation decision-making. In addition, the impact of IMO MARPOL Annex VI regulations, especially EEDI and SEEMP, is also considered in efforts to optimize energy efficiency. The method used is a mixed approach, which combines quantitative analysis of AIS data, weather reports, and fuel consumption records with machine learning algorithms for route optimization. Pearson's correlation analysis evaluates the relationship between speed, distance, travel time, and fuel consumption. Case studies are used to validate the developed model. The results showed that fuel consumption was greatly affected by the speed of the ship, with higher speeds increasing fuel consumption. A negative correlation was found between travel time and daily fuel consumption, suggesting that slower cruising can improve efficiency. The study emphasizes the importance of real-time data processing in route adjustments based on weather, congestion, and energy efficiency. This research offers an innovative, data-driven approach to route planning, different from traditional methods that rely on static charts and experience. The integration of big data in maritime logistics can reduce emissions, reduce costs, and improve operational sustainability.