Ship Route Optimization Research Articles

Tramp ship routing and speed optimization with tidal berth time windows

Tramp shipping companies need to schedule shipping routes and decide on appropriate speeds based on short-term demand. This task differs from traditional vehicle routing problems (VRPs) in that the ship may wait for the tide, which changes with time. The wait time is a nonlinear function of the load, and in this paper, we describe this kind of wait as the ship following a tidal berth time windows. Additionally, the speed of the ship affects both the wait time and the sailing cost. This paper proposes a mixed-integer nonlinear programming model to tackle this problem. A branch-and-price framework is applied to solve the model efficiently, decomposing the model into a set partitioning master problem and an elementary shortest path subproblem. A labeling algorithm incorporating ship speed is developed to handle the subproblem, and further enhancements are made by optimizing the speed separately. Computational experiments show the effectiveness and accuracy of the proposed solution approach for large-scale instances. Moreover, considering the tidal time windows allows for exploiting the practical benefits of raising tides, which benefits the tramp shipping industry.

Application of a deep learning-based discrete weather data continuousization model in ship route optimization

When ships sail across oceans, weather and sea conditions are the key factors affecting the safety and economy of ship navigation. Thus, obtaining accurate weather forecast data is very important, which can help design voyage routes. However, most weather forecast data sources only provide sparse spatio-temporal low-resolution discrete data; furthermore, as the time span increases, the resolution decreases, seriously affecting route optimization accuracy. In addition, due to maritime communication conditions, ships cannot obtain high-resolution temporal and spatial weather forecast data. Therefore, this paper introduces a transformer-based time series model to recover spatio-temporal discrete weather forecast data to improve voyage optimization accuracy. Specifically, a convolutional neural network extracts multi-dimensional spatial features from weather forecast data. The extracted features are then input into a transformer attention mechanism along the time dimension to analyze the time characteristics of the weather data. The trained model can obtain the spatiotemporal continuous model of the weather forecast data. Experimentally, the effectiveness and accuracy of the reconstructed weather forecast data were confirmed by comparing it with the observed weather data. Furthermore, the proposed method demonstrated that it is conducive to route design and optimization.

Measurement-based relationships between container ship operating parameters and fuel consumption

Increases in fuel prices and the need to decrease emissions have made the optimization of fuel consumption on ships more critical. Developing a method to accurately estimate fuel consumption in ship operations is crucial for this reason. This article determined the mathematical relationships between fuel consumption and operation parameters, such as rotational speed, draught, trim, hull fouling time, wind speed, wave height, and seawater temperature, as well as the hierarchical impact of these parameters on fuel consumption. The study used a dataset of 105,790 measurements taken on a 4,800 TEU container carrier that was in operation for 1,187 days after hull cleaning. Data-driven approaches such as Artificial Neural Networks (ANNs) and a Multiple Nonlinear Regression (MNR) with Random Search were used to develop a relationship between the ship operating parameters and fuel consumption. A comparison of statistics between the two methods showed that both ANN and MNR provided highly accurate fuel consumption estimations, with MAPE of 6.1/6.41%, RMSE of 5.01/4.98 t/day, RRMSE of 7.22/7.12%, PCC of 0.964, and R2 of 0.93. The relationships presented here could be invaluable for ship route optimization, as well as transport and air pollution studies for similarly sized container carriers.

A novel fuzzy multi-factor navigational risk assessment method for ship route optimization in costal offshore wind farm waters

The navigational risk assessment in the waters of offshore wind farms (OWFs) is difficult to be quantified due to multiple factors, to solve this problem, this paper proposes a method of ship navigational risk assessment in the waters of offshore wind farms based on multi-factor fuzzy analytic hierarchy process. First, six influence factors of navigational risk in OWFs waters are analyzed, the analytic hierarchy process (AHP) and expert evaluation table are applied to determine the weights of influence factors. Then the fuzzy comprehensive evaluation is carried out to construct the method of navigational risk assessment. Finally, a comprehensive fuzzy multi-factor method of ship navigational risk assessment in OWFs waters is developed. Taking the OWFs in Changle of Fujian Province as an experimental case study, the navigational risk before and after sailing route optimization are comprehensively evaluated, and the evaluation results show that the value of navigational risk decrease from 3.1731 to 2.0409 after the sailing route optimization. At the same time, we have proposed related navigational risk management strategies to reduce the risk of ships in the waters of wind farms based on the risk assessment results, which have important theoretical significance for the ship navigation safety supervision and management of ships in the OWFs waters and the optimization of ship sailing routes in future.

Marine route optimization using reinforcement learning approach to reduce fuel consumption and consequently minimize CO2 emissions

To meet the 2050 CO2 targets, the shipping industry which is responsible for about 3% of global CO2 emissions needs to be optimized in several aspects. Obviously, alternative fuels constitute the main measure in this respect. However, relatively high fuel prices in combination with increasing political and economic pressure may raise the need for more efficient ship operation. Ship route optimization can make an indispensable contribution to achieving this goal. In this sense, this paper applies an innovative approach for route optimization using Reinforcement Learning (RL). For this purpose, a generic ship model is first developed using Artificial Neural Networks (ANNs) to predict the fuel consumption of the ship. Moreover, various RL methods, namely Deep Q-Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO) are applied. The application of RL enables continuous action space and simultaneous optimization of ship speed and heading. DDPG demonstrates the best results as an off-policy and policy gradient method which allows a continuous action space. For example, in the fuel consumption minimization scenario without time limitation, this method can achieve savings of 6.64%. For DQN as a method with discrete action space, this value is 1.07%.

Ship route optimization using hybrid physics-guided machine learning

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.

Finding Risk-Expenses Pareto-Optimal Routes in Ice-Covered Waters

Multi-objective optimization of a vessel route is considered of key importance when creating automatic navigation systems to ensure independent navigation in ice conditions. This is explained by the need to take into account not only the time or fuel expenditures on the route but also the risks. Previously, only a few models for navigation in ice used the multi-objective approach when finding the set of Pareto-optimal solutions. This paper suggests the multi-objective model of ship routing optimization with usage of the ice chart and ship parameters. Risks for a vessel are related to values of ice thickness and ice concentration in regions to travel through, which are specified by the ice chart. In the model, we use the extended version of the wave algorithm to find a set of routes, from which we select solutions of the Pareto-front for the multi-objective problem. The model uses objective functions of route length, maximum ice thickness, and maximum ice concentration. In addition, the travel time calculations are used in the model. Kaj Riska’s model of ship performance in ice is used for calculating travel time; the speed of a vessel is evaluated in each of the graph edges. The computational example provided in the paper is based on the particular ice chart of the Gulf of Finland. The developed method can be easily implemented for assisting a particular ship in independent ice navigation with the presence of a relevant ice chart.

Energy saving method for ship weather routing optimization

In this paper, an improved three-dimensional dynamic programming algorithm for ship route optimization is proposed. As a consequence of the weather conditions and constraints, the ship course and speed are planned, and the optimal solution of ship route planning is generated. Compared with the actual navigation data of the VLCC oil tanker, the calculation accuracy of the method is verified by referring to the great circle route. Under the objective function of minimum FOC (fuel oil consumption) and ETA (estimated time of arrival), the economic benefits of the VLCC oil tanker per voyage are increased by 1.59% and 1.33% respectively, and ETA is shortened by 14.63h and 17.79h. In addition, the method also has the ability of other objective function optimization, weather updating and route updating, which can provide sufficient support for ship operators in route planning.

Tramp Ship Routing and Speed Optimization with Tidal Berth Time Windows

Tramp Ship Routing and Speed Optimization with Tidal Berth Time Windows

A Novel Fuzzy Multi-Factor Navigational Risk Assessment Method for Ship Route Optimization in Costal Offshore Wind Farm Waters

A Novel Fuzzy Multi-Factor Navigational Risk Assessment Method for Ship Route Optimization in Costal Offshore Wind Farm Waters

A Comprehensive Approach to Account for Weather Uncertainties in Ship Route Optimization

This work aims at defining in a probabilistic manner objectives and constraints typically considered in route optimization systems. Information about weather-related uncertainties is introduced by adopting ensemble forecast results. Classical reliability methods commonly used in structural analysis are adopted, allowing to achieve a simple yet effective evaluation of the probability of failure and the variability associated with the predicted fuel consumption and time of arrival. A quantitative example of application is provided, taking into consideration one of the main North Atlantic routes.

Investigating optimum ship route in the Antarctic in presence of sea ice and wind resistances – A case study between Bharati and Maitri

This paper presents a technique of ship route optimization in the Antarctic sea ice region using Dijkstra's algorithm. It studies some of the major parameters that cause resistance to the ship movement through sea ice. It aims to optimize a safe ship route in the Antarctic sea ice between Bharati and Maitri (Indian Research Stations in Antarctica) coasts. The study region is divided into grids that results into unique nodes, which are studied for sea ice parameters and wind velocity. Resistances caused due to ice and wind are considered to calculate expected ship velocity between nodes. The calculated ship velocities are then used to estimate durations to cover distances from a node to all the neighboring nodes. It forms a mathematical route from source to destination through various nodes with time as weight that is then optimized through Dijkstra's algorithm to obtain optimal route. Satellite remote sensing data derived sea ice parameters (Scatsat-1 derived sea ice extent and NSIDC sea ice concentration) and modeled wind velocity (from ECMWF) have been used as inputs in this model. Ship parameters of Kapitan Khlebnikov (Russian icebreaker) are used to test and compare the proposed model. Results of model are validated with the actual ship route navigated by the 33rd Indian Scientific Expedition to Antarctica (33ISEA) ship. The proposed algorithm, which provides an optimal route when ship parameters are known in advance, can be useful to support future ship navigation in the Antarctic sea ice including Indian Scientific Expeditions to Antarctica.

Green maritime: a routing and speed multi-objective optimization strategy

The purpose of this paper is to develop a ship routing and speed multi-objective optimization model that considers ECA (Emission Control Area) regulations, which can realize the minimization of both shipping costs and emissions. This proposed model can help maritime regulators, such as those who work in maritime departments, to trade-off shipping costs for the minimization of CO2 and SOx emissions by selecting appropriate routes and speeds. The total costs are the sum of the fuel costs, fixed time costs, and cargo inventory costs. The difference between the significance of SOx emissions inside and outside ECAs was considered. The Non-dominated Sorting Genetic Algorithm II (NSGAII) was used to obtain the Pareto-optimal set of the multi-objective optimization model and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) was used to find the trade-off solution from the Pareto-optimal set. The model was applied for a case study of a service route from Halifax, Nova Scotia, Canada to Brunswick, Georgia, United States. Compared to an actual scenario without any optimization, the results show that the model can simultaneously reduce a ship’s total costs and emissions, as well as avoid increase in the total costs that accompany increase in fuel prices. Moreover, the model can provide different optimal routes and speeds for different levels of ship emissions (CO2 and total SOx inside ECAs).

A multi-objective routing optimization model for ship intelligent navigation

In order to solve the problem of ship route planning in the autonomous navigation and decision-making of ships, based on the electronic chart display and information system (ECDIS), the meteorological conditions of ocean-going ships were analyzed and the grid method was used to establish an environmental model. The voyage time, fuel consumption and navigation safety were taken as optimization goals, and a multi-objective ship route optimization model was established, then the non-dominated sorting genetic algorithm with elite strategy (NSGA-II) was applied in the optimization route searching to realize the solution of the optimal ship route.

Ship route and speed multi-objective optimization considering weather conditions and emission control area regulations

ABSTRACT The purpose of this paper is to design a route and speed optimization method to simultaneously reduce sailing cost and time, considering Emission Control Areas (ECAs) regulations and weather conditions. To solve it, the Non-dominated Sorting Genetic Algorithm (NSGA-II) was used to find the Pareto-optimal set, and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was used to find the trade-off solution from the Pareto-optimal set. The proposed model was then applied to a service route around the US Coast, based on different fuel prices in ECAs. The results show that the proposed method can reduce the total sailing cost and time compared with other methods, and can help shipping companies effectively cope with fuel price fluctuations. Moreover, we also determined the best time interval for changing ship route and speed in terms of minimizing the sailing cost.

Sea Captains’ Views on Automated Ship Route Optimization in Ice-covered Waters

Safety in ice-covered polar waters can be optimised via the choice of a ship's route. This is of utmost importance for conventional as well as autonomous ships. However, the current state of the art in e-Navigation tools has left two open questions. First, what essential information are these tools still missing, and second, how they are seen by sea captains. In order to address these questions, we organised an ice navigation workshop to systematically collect routing justifications given by and waypoints planned by experienced sea captains that are particularly seasoned in ice navigation. Here, we report the outcome of that workshop. Our key findings include the reasoning and the commentary of the participants in looking for a better and safer route. These comments shed light upon both the official and unofficial code of conduct in open waters and boil down into a list of additional prerequisite information if further steps towards system autonomy are sought. Finally, the expert-planned waypoints are to be published alongside this paper to act as a benchmark for future maritime studies.

Finding safe and efficient shipping routes in ice-covered waters: A framework and a model

Safety for conventional and autonomous navigation in ice-covered waters is a topic of rising importance. Here, we propose a generic extendable framework to provide the optimal route from multiple route planning objectives. These objectives are attained by an evaluation of multi-source input data, including state-of-the-art model data for ice conditions, for bathymetric knowledge, and for ship-ice interaction. Additionally, we model the ship-ship interactions statistically using a mean-field, to account for ships (indirectly) assisting each other via artificial ice channels. For the subsequent pathfinding problem, we propose a new A*-based algorithm that yields output which is not dependent on the grid format of the input data but instead consists of a path that follows the Earth's curvature. The outputs of the algorithm are a set of waypoints (representing the optimal route), the travel costs (expressed in time), and the additional travel cost estimates caused by route deviation, should the optimal route be altered in any way. The steaming speeds, the optimal route, and the deviation times are represented with two-dimensional (2D) maps. Finally, we provide a model implementation of our framework as a Matlab-package, ICEPATHFINDER, that is suitable for both operational and strategic ship route optimization.

Ship weather routing using pathfinding algorithms: the case of Barcelona – Palma de Mallorca

Abstract Weather ship routing has become a recognized measure to target safe, sustainable and economical ship activities. Academic research has focused the ship routing optimization through pathfinding algorithms which take into account the meteo-oceanographic forecasts (i.e. wind, waves or currents predictions). This contribution shows the results of the numerical simulations carried out during the development of a weather ship routing applied to a ferry service in the Mediterranean Sea: Barcelona – Palma de Mallorca. From a methodological point of view, the pathfinding A* algorithm is applied to optimize the travel time considering the wave action. Under severe weather conditions, a reduction of the 7% of the travel time is obtained comparing the optimized route and the minimum distance route. The results show also a non-significant correlation between the travel time reduction and wave height. In consequence the benefit of ship routing depends not only of the wave height but also in the spatial sequence of the storm.

A multiple ship routing and speed optimization problem under time, cost and environmental objectives

The purpose of this paper is to investigate a multiple ship routing and speed optimization problem under time, cost and environmental objectives. A branch and price algorithm as well as a constraint programming model are developed that consider (a) fuel consumption as a function of payload, (b) fuel price as an explicit input, (c) freight rate as an input, and (d) in-transit cargo inventory costs. The alternative objective functions are minimum total trip duration, minimum total cost and minimum emissions. Computational experience with the algorithm is reported on a variety of scenarios.

Development of a ship weather routing system

A ship route optimization system aimed at facing the challenges of a demanding maritime trade is presented. The paper describes the complete on-board ship weather routing system highlighting the last updates, which are aimed to give it an operational perspective. Ship responses are modelled for any sea-state condition, taking into account the wave directional spreading. The functionalities of a robust multi-objective evolutionary algorithm are exploited to approximate the most favourable set of solutions, successively ranked according to the ship's requirements. The code modularity allows a great flexibility in the treatment of goals and objectives as well as in the input selection.