Integration of photovoltaic (PV) systems, desalination technologies, and Artificial Intelligence (AI) combined with Machine Learning (ML) has introduced a new era of remarkable research and innovation. This review article thoroughly examines the recent advancements in the field, focusing on the interplay between PV systems and water desalination within the framework of AI and ML applications, along with it analyses current research to identify significant patterns, obstacles, and prospects in this interdisciplinary field. Furthermore, review examines the incorporation of AI and ML methods in improving the performance of PV systems. This includes raising their efficiency, implementing predictive maintenance strategies, and enabling real-time monitoring. It also explores the transformative influence of intelligent algorithms on desalination techniques, specifically addressing concerns pertaining to energy usage, scalability, and environmental sustainability. This article provides a thorough analysis of the current literature, identifying areas where research is lacking and suggesting potential future avenues for investigation. These advancements have resulted in increased efficiency, decreased expenses, and improved sustainability of PV system. By utilizing artificial intelligence technologies, freshwater productivity can increase by 10 % and efficiency. This review offers significant and informative perspectives for researchers, engineers, and policymakers involved in renewable energy and water technology. It sheds light on the latest advancements in photovoltaic systems and desalination, which are facilitated by AI and ML. The review aims to guide towards a more sustainable and technologically advanced future.
Accurate price forecasts on the EU ETS market are of interest to many production and investment entities. This paper describes the day-ahead carbon price prediction based on a wide range of fuel and energy indicators traded on the Intercontinental Exchange market. The indicators are analyzed in seven groups for individual products (power, natural gas, coal, crude, heating oil, unleaded gasoline, gasoil). In the proposed approach, by combining the Principal Component Analysis (PCA) method and various methods of supervised machine learning, the possibilities of prediction in the period of rapid price increases are shown. The PCA method made it possible to reduce the number of variables from 37 to 4, which were inputs for predictive models. In the paper, these models are compared: regression trees, ensembles of regression trees, Gaussian Process Regression (GPR) models, Support Vector Machines (SVM) models and Neural Network Regression (NNR) models. The research showed that the Gaussian Process Regression model turned out to be the most advantageous and its price prediction can be considered very accurate.