Fig 1 - uploaded by Pauline Røstum Bellingmo
Content may be subject to copyright.
Illustration of splitting of an individual trip into acceleration, transit, and retardation phase. The top panel shows the position of the vessel during the trip. The departure point is in the lower left corner. The bottom panel shows the vessel speed (solid line) and power output of the vessels propulsion system (dashed). Both graphs are normalised by the average values of the respective variables. The black dashed lines (bottom panel) and circles (top panel) indicate the time and position of the start of different phases, respectively.
Source publication
This paper presents a method for energy efficient routing of a symmetrical electrical car ferry in Norway. Historical and operational data from the ferry and environmental data (wind, current, and waves) have been used to develop a machine learning model that predicts the energy consumption. Data from more than 2000 trips have been used for trainin...
Citations
... Recent research studies [15], [16] have explored energyefficient routing for an electric ferry in Western Norway. They rely on operational data from onboard measurements and environmental conditions from the Norwegian Meteorological Institute, and proposed a hybrid physics-guided machine learning model for optimizing the ship route. ...
Several approaches have been developed for improving the ship energy efficiency, thereby reducing operating costs and ensuring compliance with climate change mitigation regulations. Many of these approaches will heavily depend on measured data from onboard IoT devices, including operational and environmental information, as well as external data sources for additional navigational data. In this paper, we develop a framework that implements time-series analysis techniques to optimize the vessel's speed profile for improving the vessel's energy efficiency. We present a case study involving a real-world data from a passenger vessel that was collected over a span of 15 months in the south of Sweden. The results indicate that the implemented models exhibit a range of outcomes and adaptability across different scenarios. The findings highlight the effectiveness of time-series analysis approach for optimizing vessel voyages within the context of constrained landscapes, as often seen in short-sea shipping.
This is a preprint of a potential publishable work for IEEE Transactions and Journals.
... Recent research studies [9,14] have explored energy-efficient routing for an electric ferry in Western Norway. They rely on operational data from onboard measurements and environmental conditions from the Norwegian Meteorological Institute, interpolated to the nearest temporal and spatial resolutions of the vessel's onboard data. ...
... These heatmaps also show that the model's performance is sensitive to changes in the hyperparameters, indicating the importance of carefully tuning the ANN model to achieve optimal results. Tables 8,9, and 10 present the results of all twelve ANN regression models. The fourth case of inputs (IV), which considers operational and weather variables from onboard and external sources, led to the best performance (i.e., R 2 = 0.8088 and M AE = 0.0516) for estimating EngineFuelRate, as shown in Table 8. ...
The maritime industry is under pressure to increase energy efficiency for climate change mitigation. Navigational data, combining vessel operational and environmental measurements from onboard instruments and external sources, are critical for achieving this goal. Short-sea shipping presents a unique challenge due to the significant influence of surrounding landscape characteristics. With high-resolution onboard data increasingly accessible through IoT devices, appropriate data representations and AI/ML analytical tools are needed for effective decision support. The aim of this study is to investigate the fuel consumption estimation model's role in developing an energy efficiency decision support tool. ML models that lack explainability may neglect important factors and essential constraints, such as the need to meet arrival time requirements. Onboard weather measurements are compared to external forecasts , and our findings demonstrate the necessity of eXplainable Artificial Intelligence (XAI) techniques for effective decision support. Real-world data from a short-sea passenger vessel in southern Sweden, consisting of 1754 voyages over 15 months, are used to support our conclusions.
... As originally presented in [2], an overview of the state-of-the-art optimization methods used in weather routing has been presented in [3], while a weather routing system based on travel time, added resistance, and safety is developed in [4]. Many of the related works for weather routing revolve around long-distance route optimization where a large reduction in energy consumption can be achieved by avoiding the roughest environmental conditions. ...
... Moreover, passenger comfort is not included in the optimization schema, but low energy consumption is often correlated with low environmental disturbances, which in turn increase the comfort level. For the ferry route used in this work, transit is the longest and most energy consuming phase (75 % to 80 % of the overall propulsion energy used for an individual trip) with the most intricate interplay between vessel and environmental forces [2]. Consequently, we only focus on the transit phase in this paper. ...
... This paper is a continuation of the work done in [2]. In this study, draft, trim and wind measurements are collected from the ship in addition to the other ship data. ...
This paper presents a method for energy efficient weather routing of a ferry in Norway. Historical operational data from the ferry and environmental data are used to develop two models that predict the energy consumption. The first is a purely data-driven linear regression energy model, while the second is as a hybrid model, combining physical models with data-driven models using machine learning techniques. With an established energy model, it is possible to develop a route optimization that proposes efficient routes with less energy usage compared to fixed speed and heading control.
... This study presents results from a research project named Smartshiprouting (THE RESEARCH COUNCIL OF NORWAY, 2019). The work in this paper is a continuation of the weather routing system described in (Bellingmo et al., 2021) and (Jørgensen et al., 2022). The previous papers have described the development of three different models used to predict the energy consumption of a ferry in the transit phase. ...
... Data from more than 2200 trips have been gathered and used for establishing the energy model, training, and testing. The weather routing system is developed for the transit phase, as it is the longest and most energy consuming phase with the most intricate interplay between vessel and environmental forces (Bellingmo et al., 2021). It should be noted that this weather routing system has been developed for research purposes and it is not currently used in operation. ...
... Three energy models used to predict the energy consumption of a ferry have been developed (Bellingmo et al., 2021;Jørgensen et al., 2022). This includes a linear regression model, a hybrid model, and a simulation model. ...
A weather routing system for a ferry in Norway has been developed. In this paper three different models for estimating the energy consumption have been evaluated. The three energy models include two data-driven models, i.e., a linear regression model and a hybrid model, and a simulation-based energy model. The hybrid energy model performed best with the highest accuracy and at the lowest run time. Moreover, using the hybrid energy model, the weather routing system has been tested and evaluated. The results show typical energy savings up to 1,5% are achieved.
The maritime industry is under pressure to increase energy efficiency for climate change mitigation. Navigational data, combining vessel operational and environmental measurements from onboard instruments and external sources, are critical for achieving this goal. Short-sea shipping presents a unique challenge due to the significant influence of surrounding landscape characteristics. With high-resolution onboard data increasingly accessible through IoT devices, appropriate data representations and AI/ML analytical tools are needed for effective decision support. The aim of this study is to investigate the fuel consumption estimation model’s role in developing an energy efficiency decision support tool. ML models that lacking explainability may neglect important factors and essential constraints, such as the need to meet arrival time requirements. Onboard weather measurements are compared to external forecasts, and our findings demonstrate the necessity of eXplainable Artificial Intelligence (XAI) techniques for effective decision support. Real-world data from a short-sea passenger vessel in southern Sweden, consisting of 1754 voyages over 15 months (More of data description and code sources of this study can be found in the GitHub repository at https://github.com/MohamedAbuella/ST4EESSS), are used to support our conclusions.
This paper presents a literature review on the use of green technologies in maritime transportation planning. We first provide an overview and evaluation of the most relevant green technologies. Next, we discuss the implications and differences of each technology on the planning problems of maritime transportation. Our review highlights the need for integrating planning problems in green maritime transportation, as green technologies may require different planning approaches to address technological and price uncertainties. We also emphasize the importance of developing new mathematical models and optimization strategies to capture the unique complexities of planning problems in this context.
