Data-driven ship berthing forecasting for cold ironing in maritime transportation

Cold ironing (CI) is an electrification alternative in the maritime sector used to reduce shipborne emissions by switching from fuel electricity when a ship docks at port. During ship’s berthing mode of operation, accurately estimating duration could assist port operator manage berth allocation and energy scheduling optimally. However, involvement multiple input parameters with large dataset requires suitable handling method. Thus, this paper proposed data-driven approach for forecasting cold various models such as artificial neural networks, linear regression, random forest, decision tree, extreme gradient boosting. Meanwhile, RMSE MAE are two main indicators applied assess accuracy. The simulation-based result shows that network outperforms all other lowest error performance (3.1343) (0.2548), suggesting its capability handle nonlinearities complex problems activity. high accuracy output study, which contributes close estimation info: 1) CI power consumption 2) departure time ship. This information vital be management system (EMS) well problem (BAP).