Modelagem estatística em dados de energia solar

Abstract

Nowadays, most of the energy used in the world comes from conventional sources (nonrenewable sources and fossil fuels such as petroleum, mineral coal and natural gas), however one of the main ways of generating clean energy is through solar energy, that in turn is an inexhaustible energy source. In the present work, we are interested in modeling the data from the solar energy generation in a residence located in Serra de São Bento-RN, using different distributions of probability. The distributions that will be used were chosen based on the set of data under study. The criteria for selection of the distribution that best fits to the data are the visual analysis of curves adjusted in relation to the empirical distributions, as well as application of the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC).