Nowadays, millions of photovoltaic (PV) plants are installed around the world. Given the widespread use of PV supply systems and in order to keep these PV plants safe and to avoid power losses, they should be carefully protected, and eventual faults should be detected, classified and isolated. In this paper, different machine learning (ML) and deep learning (DL) techniques were assessed for fault detection and diagnosis of PV modules. First, a dataset of infrared thermography images of normal and failure PV modules was collected. Second, two sub-datasets were built from the original one: The first sub-dataset contained normal and faulty IRT images, while the second one comprised only faulty IRT images. The first sub-dataset was used to develop fault detection models referred to as binary classification, for which an image was classified as representing a faulty PV panel or a normal one. The second one was used to design fault diagnosis models, referred to as multi-classification, where four classes (Fault1, Fault2, Fault3 and Fault4) were examined. The investigated faults were, respectively, failure bypass diode, shading effect, short-circuited PV module and soil accumulated on the PV module. To evaluate the efficiency of the investigated models, convolution matrix including precision, recall, F1-score and accuracy were used. The results showed that the methods based on deep learning exhibited better accuracy for both binary and multiclass classification while solving the fault detection and diagnosis problem in PV modules/arrays. In fact, deep learning techniques were found to be efficient for the detection and classification of different kinds of defects with good accuracy (98.71%). Through a comparative study, it was confirmed that the DL-based approaches have outperformed those based on ML-based algorithms.

The scarcity of drinkable water supplies is becoming a serious and troubling challenge to long-term development. This issue emphasises the urgency of implementing rapid water desalination options. However, desalination is a capital-intensive process that requires a significant amount of energy, and since it is now mostly powered by fossil fuels across the globe, it has the potential to leave a significant carbon footprint. In this light, transitioning to green energy sources for desalination is a necessity in today’s society. Humidification–dehumidification (HD) is one of the most effective desalination procedures to consider for distant places with modest fresh water demands for household and agricultural demands. This is mostly because it requires minimal operational and maintenance concerns. The current article examines the many kinds of HD desalination systems driven by solar energy sources and their key components. The current study established that the seawater HD system is viable for producing fresh water, especially for greenhouses and dispersed demand. HD is an effective technique for eluting fresh water from concentrated brines, boosting production, and minimising harmful environmental impact, benefitting ecosystems and human services. The packed bed humidifier is the most commonly used kind of humidifier in the HD water desalination system. Additionally, as compared to an indirect dehumidifier, the direct dehumidifier improves the performance of the HD desalination system. According to the findings of this research, hybrid energy systems have the greatest gain output ratio (GOR). Solar water heating significantly increases system productivity as compared to solar air heating. When combined with a heat pump, the HD delivers optimal system productivity and GOR at the lowest cost per litre. The conclusion is that, even though humidification–dehumidification is a promising method for decentralised small-scale fresh water production applications, it needs additional improvement to optimise system performance in terms of economy and gain output ratio.