Advanced machine learning techniques for predicting power generation and fault detection in solar photovoltaic systems

Abstract This study investigated the application of advanced Machine Learning techniques to predict power generation and detect abnormalities in solar Photovoltaic systems. The study conducted a comprehensive assessment of various sophisticated models, including Random Trees, Random Forest, eXtreme Gradient Boosting, Linear Regression, Gradient Boosting (GB), and Categorical Boosting (CatBoost), utilizing a substantial dataset of 97,333 sets. The analysis focused on two fundamental objectives: power prediction and fault identification, both of which are crucial for enhancing the effectiveness and dependability of PV systems. CatBoost and GB models exhibited exceptional performance in power prediction, with the maximum R-squared value of 0.994. Demonstrating a strong correlation with the data and the ability to account for a substantial amount of the variation in power generation. These models outperformed others by providing more accurate and reliable projections, which are crucial for effective solar energy management and planning. CatBoost demonstrated superior performance compared to other approaches in the flaw detection test, attaining the highest performance metrics. The model achieved an accuracy of 0.999743, precision of 0.997171, recall of 0.999291, and an F1 score of 0.998230. The measures illustrated CatBoost’s exceptional ability to precisely identify problems with little errors, confirming it as the most successful model among those evaluated. The exceptional precision and dependability of the CatBoost model in identifying faults highlighted its capacity for continuously monitoring and maintaining solar systems in real-time, consequently augmenting operational efficiency. The study emphasized the significance of choosing suitable models to achieve the highest level of accuracy in predicting and detecting faults, thereby enabling the development of more sustainable and efficient solar energy systems. Subsequent research should prioritize the validation of these models using varied datasets, integration of up-to-date meteorological data, and creation of defect detection methods in real-time to enhance system efficiency.