Photovoltaic (PV) systems represent one of the pillars of the global energy transition, yet their reliability and long-term efficiency are constantly threatened by hidden defects and progressive degradation. Early and precise identification of such anomalies is essential for ensuring safety, enhancing performance, and facilitating predictive maintenance plans. Infrared thermography (IRT) is a non-invasive and cost-effective technique for the inspection of PV modules. This study proposes an efficient attentive U-Net architecture for the semantic segmentation of thermographic images, aimed at supporting predictive maintenance and power loss assessment. The model integrates squeeze-and-excitation (SE) and attention gate (AG) modules with atrous spatial pyramid pooling (ASPP), achieving an optimal balance between accuracy and computational complexity. A comprehensive ablation study, including input resolution and module combinations, was conducted on a dataset of 500 thermograms annotated into six defect classes. The proposed configuration (256 × 256 input) achieved a mean Intersection over Union (mIoU) of 81.4% and a macro-F1 score of 87.5%, outperforming U-Net and DeepLabv3+ by over 4 percentage points, with only 5.24 M parameters and an inference time of 118.6 ms per image. These results confirm the suitability of the framework for energy-oriented fault diagnosis and near real-time monitoring of photovoltaic plants.

The rapid growth of renewable energy integration in modern power systems brings new challenges in terms of stability and quality of electricity supply. Hybrid AC/DC microgrids represent a promising solution to integrate photovoltaic panels (PV), wind turbines, fuel cells, and storage units with flexibility and efficiency. However, maintaining adequate power quality (PQ) under variable conditions of generation, load, and grid connection remains a critical issue. This paper presents the modelling, implementation, and validation of a hybrid AC/DC microgrid equipped with a fuzzy-logic-based energy management system (EMS). The study combines PQ assessment, measurement architecture, and supervisory control for technical compliance and economic efficiency. The microgrid integrates a combination of PV array, wind turbine, proton exchange membrane fuel cell (PEMFC), battery storage system, and heterogeneous AC/DC loads, all modelled in MATLAB/Simulink using a physical-network approach. The fuzzy EMS coordinates distributed energy resources by considering power imbalance, battery state of charge (SOC), and dynamic tariffs. Results demonstrate that the proposed controller maintains PQ indices within IEC/IEEE standards while eliminating short-term continuity events. The proposed EMS prevents harmful deep battery cycles, maintaining SOC within 30–90%, and optimises fuel cell activation, reducing hydrogen consumption by 14%. Economically, daily operating costs decrease by 10–15%, grid imports are reduced by 18%, and renewable self-consumption increases by approximately 16%. These findings confirm that fuzzy logic provides an effective, computationally light, and uncertainty-resilient solution for hybrid AC/DC microgrid EMS, balancing technical reliability with economic optimisation. Future work will extend the framework toward predictive algorithms, reactive power management, and hardware-in-the-loop validation for real-world deployment.

The global energy landscape is increasingly shaped by renewable energy sources, particularly photovoltaic systems, which are influenced by economic, environmental and geopolitical factors. Technological advances and political incentives have reduced the cost of photovoltaic systems and driven their integration into the energy grid. This trend has been accelerated by energy crises and geopolitical events, underlining the importance of energy security and diversification of energy sources. However, the inherent variability of solar energy, which depends on climatic and natural cycles, poses a major challenge for the management of energy production. In this paper, short-term forecasting models for photovoltaic power plants are developed and applied using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) system. These models improve grid management by predicting photovoltaic output more accurately, enabling better integration and reducing dependence on balancing power plants, thereby optimising cost efficiency and reliability. A novel approach for fine-tuning the models at different geographical locations is presented, where the pre-trained models are adapted to local datasets to maintain forecast accuracy despite varying climatic conditions. The evaluation results show that the fine-tuned CNN-LSTM model achieves a mean absolute error (MAE) of 242.46 W, a root mean square error (RMSE) of 406.63 W and an R2 value of 0.78, indicating a significant improvement in forecast accuracy over the baseline model. This robust framework demonstrates the practical applicability of the model for real-world photovoltaic power generation forecasting, highlighting the importance of fine-tuning to local conditions.

With the increasing integration of photovoltaic (PV) systems into power grids, accurate short-term forecasting of solar irradiance is essential for efficient energy management. This paper presents a machine learning model developed using a synthetic dataset designed to analyze the potential of multi- camera sky imaging for regional solar irradiance forecasting. The dataset, generated in a controlled simulation environment, cap- tures cloud dynamics and solar irradiance at multiple locations within a given region. The proposed model utilizes sky images from multiple virtual cameras strategically positioned to provide spatially distributed observations. By combining image-based features with historical irradiance measurements, the model shows improved forecasting accuracy compared to single-camera approaches. The results indicate that multi-camera systems better capture the spatial variability of cloud cover and allow the model to predict solar irradiance for locations without installed cameras. This research highlights the potential of multi-camera configurations for regional forecasting and provides valuable insights for grid operators and energy planners. The results support the adoption of distributed sky imaging networks as a practical approach to improve solar irradiance predictions and ultimately contribute to the stability and reliability of solar-powered energy systems through improved forecast accuracy.