Digital twin-based energy efficiency evaluation for vessel operations in container terminals

Abstract

To tackle high energy consumption and carbon emissions during vessel berthing, this study proposes a digital twin (DT)-driven intelligent energy assessment system for ports. The framework integrates physical-layer sensor networks with virtual-layer high-fidelity models and machine learning to dynamically optimize energy efficiency against historical benchmarks. It introduces a Value-added Energy Efficiency Index (VAEEI) and a dual-dimensional evaluation model that links port operations with energy consumption. Unlike static methods, the system enables real-time lifecycle energy management by resolving multi-source dynamic factor interactions, including vessel characteristics and terminal coordination. Validated at a Yangtze River automated container terminal, the solution reduces technical bottlenecks in energy-activity correlation modeling and supports low-carbon decision-making. This research extends DT applications in maritime energy governance, establishes a methodological framework for smart ports, and advances green shipping transformation through data-driven operational optimization.