The introduction of green hydrogen-based energy storage in association with renewable energy constitutes a promising and sustainable solution to the increase in energy demand while reducing greenhouse gas emissions. However, these hybrid systems face technical, economic, and logistic challenges that require a new transport and distribution architecture. The technical-economic study of these expensive installations requires good modeling and optimal sizing of the system components. This study presents a global model for hydrogen production and storage stations using photovoltaics (PV) and integrating Proton Exchange Membrane Fuel Cell (PEMFC) modules for electric vehicles. The simulations and sizing were based on the implementation of an effective mathematical model capable of accurately simulating the real dynamic behavior of the installation, the electrical and energy yields, the power consumed and produced, and finally the mass of hydrogen stored and/or consumed by the fuel cell. In this model, the hybrid system integrates PV solar panels with a maximum power of 1.2 MW, followed by a 1.0 MW Proton Exchange Membrane (PEM) electrolyzer, a high-pressure hydrogen storage tank, and a PEMFC to convert hydrogen into electricity. The simulation results showed that the energy generated by the PV panels can produce around 200 kg/day of green hydrogen by electrolysis, which makes it possible to power 100 electric cars per day with a range of 250 km for each.

This paper addresses the multi-target tracking problem in a multiple-input multiple-output radar system. Different tracking sensor measurements often encounter complex data as well correlation problems. Our goal is to solve this dilemma, which appears to be a new technical challenge; fix object-tracking scenarios while avoiding divergence. Once the cross-path phenomenon occurs, the target measurement assignment process in MIMO radar systems becomes more complicated. Therefore, this interference phenomenon can disturb the received signal and miss the state estimation process. To avoid all the mentioned problems, we have improved a new hybrid algorithm based on the particle filter; Adaptive Monte Carlo has been used in conjunction with the Joint Probabilistic Data Association Filter to substitute the classical extended KALMAN filter combined with JPDAF known as EKF-JPDAF. Experimental results of our MIMO-FMCW radar system with AMC-JPDAF converge to a more accurate state estimate while avoiding divergence. Using MATLAB software development framework, the designed system meets the goals originally set by AMC-JPDAF by referring to the experimental database obtained from the MIMO-FMCW 8x16 radar system.

The increasing penetration of photovoltaic (PV) systems requires accurate and stable short-term forecasting to ensure reliable grid operation under operational constraints. This paper investigates short-horizon multi-step PV power forecasting using one full year of high-resolution (5 min) real-world data from a 111-kW grid-connected rooftop installation. The forecasting problem is formulated as a direct multi-output supervised learning task with a 30 min prediction horizon. A comprehensive comparative evaluation is conducted across baseline (persistence), tree-based (XGBoost), and deep learning architectures (LSTM, GRU, and Temporal Convolutional Networks—TCN). Results show that deep learning models significantly outperform conventional baselines, with LSTM achieving the lowest normalized RMSE (≈10.3%), while TCN provides a competitive trade-off between predictive accuracy, temporal stability, and computational efficiency. The direct multi-step formulation was adopted to reduce potential error propagation effects commonly observed in recursive forecasting approaches. Beyond forecasting accuracy, the study evaluates computational complexity and inference latency to assess practical deployability in resource-constrained environments. The proposed framework demonstrates that high-resolution real-world PV forecasting can achieve both strong predictive performance and operational feasibility. These findings contribute to the development of robust short-term forecasting strategies for distributed renewable energy systems operating under regulatory export constraints.

Several tools have been introduced to achieve early detection of voice disorders. Among these tools are the human factor cepstral coefficients HFCC combined with prosodic parameters, the noise-harmonic ratio (NHR), the harmonic-noise ratio (HNR), analysis of trend fluctuations (DFA) and fundamental frequency (F0). These parameters are introduced and calculated in every frame. In this work, we used a variation of HFCC called equivalent rectangular bandwidth (ERB) to study the effects of HFCC on the classification of pathological voices. Using the HTK classifiers, the classification is carried out on two pathological databases, Massachusetts Eye and Ear Infirmary (MEEI) and Saarbruecken Voice Database (SVD). To assess the performance of the system, we used sensitivity and specificity.