Artificial Intelligence (AI) is increasingly used in online education platforms to provide valuable insights into students’ performance and success. However, the complexity of AI models makes it challenging for educators to interpret the specific factors that influence whether a student is going to pass or fail. Utilizing the Open University Learning Analytics Dataset (OULAD), this study employs various machine learning and deep learning techniques for predicting students’ success, along with SHapley Additive exPlanations (SHAP) as an Explainable Artificial Intelligence (XAI) technique, to understand the key factors behind success or failure. Unlike traditional statistical methods that explore variable relationships, this AI-driven approach uses advanced deep learning techniques to identify patterns and insights, allowing for a better understanding of the factors influencing student success. Additionally, this study focuses on identifying students at risk of failure using XAI techniques, specifically SHAP, to interpret model outputs by breaking down how specific factors contribute to a student’s success. This method enables targeted interventions to support their success. Results reveal that student engagement and registration timelines are critical factors affecting performance. The customized models achieve up to 94% accuracy for the designed tasks, outperforming traditional approaches. This study contributes to the use of AI in education and offers practical insights not only for educators but also for administrators and policymakers to enhance the quality and effectiveness of online learning.

This study presents a comparative techno-economic and environmental assessment of three leading stationary energy storage technologies: lithium-ion batteries, lead-acid batteries, and hydrogen systems (electrolyzer–tank–fuel cell). The analysis integrates Life Cycle Assessment (LCA) and Levelized Cost of Storage (LCOS) to provide a holistic evaluation. The LCA covers the full cradle-to-grave stages, while LCOS accounts for capital and operational expenditures, efficiency, and cycling frequency. The results indicate that lithium-ion batteries achieve the lowest LCOS (120–180 EUR/MWh) and high round-trip efficiency (90–95%), making them optimal for short- and medium-duration storage. Lead-acid batteries, though characterized by low capital expenditures (CAPEX) and high recyclability (>95%), show limited cycle life and lower efficiency (75–80%). Hydrogen systems remain costly (>250 EUR/MWh) and less efficient (30–40%), yet they demonstrate clear advantages for long-term and seasonal storage, particularly under scenarios with “green” hydrogen production and reduced CAPEX. These findings provide practical guidance for policymakers, investors, and industry stakeholders in selecting appropriate storage solutions aligned with decarbonization and sustainability goals.

Power electronics plays a key role in the management and conversion of electrical energy in a variety of applications, including the use of renewable energy sources such as solar, wind and hydrogen energy, as well as in electric vehicles, industrial technologies, homes and smart grids. These technologies are essential for the successful implementation of the green transition, as they help reduce carbon emissions and promote the production and consumption of cleaner and more sustainable energy. The present work presents a new generation of power electronic devices and systems, which includes the following main aspects: advances in semiconductor technologies, such as the use of silicon carbide (SiC) and gallium nitride (GaN); nanomaterials for the realization of magnetic components; using a modular principle to construct power electronic devices; applying artificial intelligence techniques to device lifecycle design; and the environmental aspects of design. The new materials allow the devices to operate at higher voltages, temperatures and frequencies, making them ideal for high-power applications and high-frequency operation. In addition, the development of integrated and modular power electronic systems that combine energy management, diagnostics and communication capabilities contributes to the more intelligent and efficient management of energy resources. This includes integration with the Internet of Things (IoT) and artificial intelligence (AI) for automated task solving and work optimization.

The electricity load forecasting handles the process of determining how much electricity will be available at a given time while maintaining the balance and stability of the power grid. The accuracy of electricity load forecasting plays an important role in ensuring safe operation and improving the reliability of power systems and is a key component in the operational planning and efficient market. For many years, a conventional method has been used by using historical data as input parameters. With swift progress and improvement in technology, which shows more potential due to its accuracy, different methods can be applied depending on the identified model. To enhance the forecast of load, this paper introduces and proposes a framework developed on graph database technology to archive large amounts of data, which collects measured data from electrical substations in Pristina, Kosovo. The data includes electrical and weather parameters collected over a four-year timeframe. The proposed framework is designed to handle short-term load forecasting. Machine learning Linear Regression and deep learning Long Short-Term Memory algorithms are applied to multiple datasets and mean absolute error and root mean square error are calculated. The results show the promising performance and effectiveness of the proposed model, with high accuracy in load forecasting.

Piezoelectric energy harvesters have been extensively researched for use with wireless sensors or low power consumption electronic devices. Most of the piezoelectric energy harvesters cannot generate enough power for potential applications. In this study, we explore the parameters, including gap and proof mass, that can affect the damping of the cantilever to optimize the design of the energy harvester. A finite analysis is conducted using COMSOL Multiphysics software. Usually, this type of simulation is performed using the loss factor. However, it is known that results from the loss factor produce models that do not fit the experimental data well. In fact, the result of output voltage using the loss factor is 50% higher than the real value, which is due to ignoring the adverse effect of a superimposing mechanical damping of different constituent materials. In order to build a true model, Rayleigh damping coefficients are measured to use in a simulation. This resulted in a closer fit of modeling and experimental data, and a 5 times better output voltage from the optimized energy harvester compared with using the smallest gap and mass.

This paper presents a numerical study of the effect of the transmission configuration on the energy consumption of an electric vehicle. The first part of this study is related to a vehicle simulation model that takes into consideration vehicle resistances such as aerodynamic, rolling and inertial resistance as well as the traction force. The model was then validated by means of vehicle acceleration time, from 0 to 100 km/h in the case of a single-speed gearbox. Vehicle power demand and electrical energy consumption were then evaluated over three standardized test cycles: WLTC-Class 3, NEDC and FTP-75. For each cycle, two cases were studied: a single-speed and dual-speed gearbox. Very different power demand was observed between the cycles in terms of maximum and average driving power. The most power-demanding cycle was WLTC, while NEDC was less power demanding. However, the specific driving energy per kilometer was very similar for NEDC and FTP-75, as it respectively accounted to 0.118/0.116 kWh/km and 0.117/0.115 kWh/km. WLTC led to a higher specific consumption of 0.127/0.124 kWh/km. A dual-speed gearbox led to better efficiency, within the range of 1.7% to 2.4%. The higher value was obtained for highly dynamic WLTC.