The use of photovoltaic systems for clean electrical energy has increased. However, due to their low efficiency, researchers have looked for ways to increase their effectiveness and improve their efficiency. The Maximum Power Point Tracking (MPPT) inverters allow us to maximize the extraction of as much energy as possible from PV panels, and they require algorithms to extract the Maximum Power Point (MPP). Several intelligent algorithms show acceptable performance; however, few consider using Artificial Neural Networks (ANN). These have the advantage of giving a fast and accurate tracking of the MPP. The controller effectiveness depends on the algorithm used in the hidden layer and how well the neural network has been trained. Articles over the last six years were studied. A review of different papers, reports, and other documents using ANN for MPPT control is presented. The algorithms are based on ANN or in a hybrid combination with FL or a metaheuristic algorithm. ANN MPPT algorithms deliver an average performance of 98% in uniform conditions, exhibit a faster convergence speed, and have fewer oscillations around the MPP, according to this research.

Knowing exactly how much solar radiation reaches a particular area is helpful when planning solar energy installations. In recent years the use of renewable energies, especially those related to photovoltaic systems, has had an impressive up-tendency. Therefore, mechanisms that allow us to predict solar radiation are essential. This work aims to present results for predicting solar radiation using optimization with the Random Forest (RF) algorithm. Moreover, it compares the obtained results with other machine learning models. The conducted analysis is performed in Queretaro, Mexico, which has both direct solar radiation and suitable weather conditions more than three quarters of the year. The results show an effective improvement when optimizing the hyperparameters of the RF and Adaboost models, with an improvement of 95.98% accuracy compared to conventional methods such as linear regression, with 54.19%, or recurrent networks, with 53.96%, without increasing the computational time and performance requirements to obtain the prediction. The analysis was successfully repeated in two different scenarios for periods in 2020 and 2021 in Juriquilla. The developed method provides robust performance with similar results, confirming the validity and effectiveness of our approach.