The urgent imperative to mitigate carbon dioxide (CO₂) emissions from power generation poses a pressing challenge for contemporary society. In response, there is a critical need to intensify efforts to improve the efficiency of clean energy sources and expand their use, including wind energy. Within this field, it is necessary to address the variability inherent to the wind resource with the application of prediction methodologies that allow production to be managed. At the same time, to extend its use, this clean energy should be made accessible to everyone, including on a small scale, boosting devices that are affordable for individuals, such as Raspberry and other low-cost hardware platforms. This study is designed to evaluate the effectiveness of various machine learning (ML) algorithms, with special emphasis on deep learning models, in accurately forecasting the power output of wind turbines. Specifically, this research deals with convolutional neural networks (CNN), fully connected networks (FC), gated recurrent unit cells (GRU), and transformer-based models. However, the main objective of this work is to analyze the feasibility of deploying these architectures on various computing platforms, comparing their performance both on conventional computing systems and on other lower-cost alternatives, such as Raspberry Pi 3, in order to make them more accessible for the management of this energy generation. Through training and a rigorous benchmarking process, considering accuracy, real-time performance, and energy consumption, this study identifies the optimal technique to accurately model such real-time series data related to wind energy production, and evaluates the hardware implementation of the studied models. Importantly, our findings demonstrate that effective wind power forecasting can be achieved on low-cost hardware platforms, highlighting the potential for widespread adoption and the personal management of wind power generation, thus representing a fundamental step towards the democratization of clean energy technologies.

This study evaluates the effectiveness of Recurrent Neural Networks (RNNs) and Transformer-based models in predicting the Air Quality Index (AQI). Accurate AQI prediction is critical for mitigating the significant health impacts of air pollution and plays a vital role in public health protection and environmental management. The research compares traditional RNN models, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, with advanced Transformer architectures. Data were collected from a weather station in Cuenca, Ecuador, focusing on key pollutants such as CO, NO2, O3, PM2.5, and SO2. Model performance was assessed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the Coefficient of Determination (R2). The findings reveal that the LSTM model achieved superior performance, with an R2 of 0.701, an RMSE of 0.087, and an MAE of 0.056, demonstrating superior capability in capturing temporal dependencies within complex datasets. Conversely, while Transformer-based models exhibited potential, they were less effective in handling intricate time-series data, resulting in comparatively lower accuracy. These results position the LSTM model as the most reliable approach for AQI prediction, offering an optimal balance between predictive accuracy and computational efficiency. This research contributes to improving AQI forecasting and underscores the importance of timely interventions to mitigate the harmful effects of air pollution.

Optimizing wind turbine control is a major challenge due to wind variability and nonlinearity. This research seeks to improve the performance of wind turbines by designing and developing hybrid intelligent controllers that combine advanced artificial intelligence techniques. A control system combining deep neural networks and fuzzy logic was implemented to optimize the efficiency and operational stability of a 3.5 MW wind turbine. This study analyzed several deep learning models (LSTM, GRU, CNN, ANN, and transformers) to predict the generated power, using data from the SCADA system. The structure of the hybrid controller includes a fuzzy inference system with 28 rules based on linguistic variables that consider power, wind speed, and wind direction. Experiments showed that the hybrid-GRU controller achieved the best balance between predictive performance and computational efficiency, with an R² of 0.96 and 12,119.54 predictions per second. The GRU excels in overall optimization. This study confirms intelligent hybrid controllers’ effectiveness in improving wind turbines’ performance under various operating conditions, contributing significantly to the field of wind energy.

Accurate forecasting of photovoltaic power, while still respecting physical laws, plays a central role in today’s energy systems. It matters for grid stability, for market participation, and for the real deployment of digital twins. Purelydata-driven models often look impressive on paper—they reach low numerical errors—but they sometimes miss what truly governs the system. They may predict output at night, misjudge inverter clipping, or forget that heat changes performance. Small details, yet crucial ones, that make these models unreliable when conditions shift.To deal with that, our work develops a Physics-Informed Residual Neural Network (PINN-Residual) built upon a hybrid DC model. It combines PVWatts’ linear temperature correction with Huld’s logarithmic refinement for low-irradiance behavior. Instead of forcing equations directly, the network learns two residual terms—multiplicative (δₐ) and additive (δᵦ)—that describe systematic gaps between the physical baseline and what sensors actually record. During training, a time-adaptive physics loss keeps those corrections from drifting too far, so the learning process stays consistent with the real plant’s dynamics.When applied to the PVOD v1.0 dataset (stations 00, 04 and 08), the model achieved high numerical accuracy (R² ≈ 0.97–0.99) while improving physical realism and smoothness through time. More interestingly, the residuals themselves carry meaning: δₐ tends to trace gradual module aging, whereas δᵦ mirrors inverter or wiring losses. What begins as a predictor ends up behaving like a diagnostic tool—one that can explain why deviations appear, not just when.Overall, the study supports physics-oriented residual learning as a dependable and interpretable path for renewable-energy forecasting. It offers an approach that remains practical for operations yet transparent enough to guide future digital-twin developments in photovoltaic plants.