In recent years, the International Maritime Organization agreed on aiming to reduce shipping’s greenhouse gas emissions by 50% with respect to 2009 levels. Meanwhile, cruise ship tourism is growing at a fast pace, making the challenge of achieving this goal even harder. The complexity of the energy system of these ships makes them of particular interest from an energy systems perspective. To illustrate this, we analyzed the energy and exergy flow rates of a cruise ship sailing in the Baltic Sea based on measurements from one year of the ship’s operations. The energy analysis allows identifying propulsion as the main energy user (46% of the total) followed by heat (27%) and electric power (27%) generation; the exergy analysis allowed instead identifying the main inefficiencies of the system: while exergy is primarily destroyed in all processes involving combustion (76% of the total), the other main causes of exergy destruction are the turbochargers, the heat recovery steam generators, the steam heaters, the preheater in the accommodation heating systems, the sea water coolers, and the electric generators; the main exergy losses take place in the exhaust gas of the engines not equipped with heat recovery devices. The application of clustering of the ship’s operations based on the concept of typical operational days suggests that the use of five typical days provides a good approximation of the yearly ship’s operations and can hence be used for the design and optimization of the energy systems of the ship.

An accurate fuel consumption prediction model is the basis for ship navigation status analysis, energy conservation, and emission reduction. In this study, we develop a black-box model based on machine learning and a white-box model based on mathematical methods to predict ship fuel consumption rates. We also apply the Kwon formula as a data preprocessing cleaning method for the black-box model that can eliminate the data generated during the acceleration and deceleration process. The ship model test data and the regression methods are employed to evaluate the accuracy of the models. Furthermore, we use the predicted correlation between fuel consumption rates and speed under simulated conditions for model performance validation. We also discuss applying the data-cleaning method in the preprocessing of the black-box model. The results demonstrate that this method is feasible and can support the performance of the fuel consumption model in a broad and dense distribution of noise data in data collected from real ships. We improved the error to 4% of the white-box model and the $R^2$ to 0.9977 and 0.9922 of the XGBoost and RF models, respectively. After applying the Kwon cleaning method, the value of $R^2$ also can reach 0.9954, which can provide decision support for the operation of shipping companies.

Internet of Things (IoT) devices are increasingly popular due to their wide array of application domains. In IoT networks, sensor nodes are often connected in the form of a mesh topology and deployed in large numbers. Managing these resource-constrained small devices is complex and can lead to high system costs. A number of standardized protocols have been developed to handle the operation of these devices. For example, in the network layer, these small devices cannot run traditional routing mechanisms that require large computing powers and overheads. Instead, routing protocols specifically designed for IoT devices, such as the routing protocol for low-power and lossy networks, provide a more suitable and simple routing mechanism. However, they incur high overheads as the network expands. Meanwhile, reinforcement learning (RL) has proven to be one of the most effective solutions for decision making. RL holds significant potential for its application in IoT device’s communication-related decision making, with the goal of improving performance. In this paper, we explore RL’s potential in IoT devices and discuss a theoretical framework in the context of network layers to stimulate further research. The open issues and challenges are analyzed and discussed in the context of RL and IoT networks for further study.

Maritime transportation is a significant contributor to SO_x, NO_x, and particle matter (PM) emissions, and to a lesser extent, of CO₂. Recently, new regulations are being enforced in special geographical areas to limit the amount of emissions from the ships. This fact, together with the high fuel prices, is driving the marine industry toward the improvement of the energy efficiency of ships. Although more sophisticated and complex engine designs can improve significantly of the energy systems on ships, waste heat recovery arises as the most effective technique for the reduction of the energy consumption. In this sense, it is estimated that around 50% of the total energy from the fuel consumed in a ship is wasted and rejected through liquid and gas streams. The primary heat sources for waste heat recovery are the engine exhaust and coolant. In this work, we present a study on the integration of an organic Rankine cycle (ORC) in an existing ship, for the recovery of the main and auxiliary engines (AE) exhaust heat. Experimental data from the engines on the cruise ship M/S Birka Stockholm were logged during a port-to-port cruise from Stockholm to Mariehamn, over a period of 4 weeks. The ship has four main engines (ME) Wärtsilä 5850 kW for propulsion, and four AE 2760 kW which are used for electrical generation. Six engine load conditions were identified depending on the ship's speed. The speed range from 12 to 14 kn was considered as the design condition for the ORC, as it was present during more than 34% of the time. In this study, the average values of the engines exhaust temperatures and mass flow rates, for each load case, were used as inputs for a model of an ORC. The main parameters of the ORC, including working fluid and turbine configuration, were optimized based on the criteria of maximum net power output and compactness of the installation components. Results from the study showed that an ORC with internal regeneration using benzene as working fluid would yield the greatest average net power output over the operating time. For this situation, the power production of the ORC would represent about 22% of the total electricity consumption on board. These data confirmed the ORC as a feasible and promising technology for the reduction of fuel consumption and CO₂ emissions of existing ships.

Large language models (LLMs) have achieved planetary popularity and have become accepted in higher education. On the basis of face-to-face interviews, a survey examining students' attitudes about the integration of LLM into education, and our own academic experience, we defined a realistic solution for creating assignments. It embraces essay writing as well as various aspects of computer programming. The experiments were carried out during the winter semester of academic 2023/24 at two universities from two different countries. This paper presents the experience gained in the creation of two different computer science assignments with and without the use of LLM. Comparative analysis refers on three approaches: traditional or manual assignment preparation without using any LLM; full reliance on LLMs; and a hybrid mode, depending on the amount of application of the LLM in the preparation of the assignment. The proposed solution was evaluated quantitatively, with the aim of becoming a benchmark for examining the integration of LLM studies into higher education. Findings reveal the importance of hybrid mode, as the most preferred approach among students.