Electrical energy generation with hydrocarbons accounts for about 38% of global CO2 emissions. Solar photovoltaic technology is a reliable alternative to reduce these emissions. To predict the electrical energy generation behavior in a photovoltaic system, we developed an adaptive neuro-fuzzy inference system (ANFIS) model which integrates an optimization through a genetic algorithm (GA). The evolutionary ANFIS-GA uses a geographical area's solar radiation and ambient temperature. This model uses the capacity for classification and identification of data patterns of neural networks, and through fuzzy modeling, it calculates the optimal membership functions and fuzzy rules. The ANFIS-GA model is developed using MATLAB® software and is trained with the acquired data weather station and the electrical power output of the photovoltaic system located in Hermosillo, Sonora, México. The above was compared under the same parameters with an ANFIS model based on a hybrid algorithm. Reach values of RSME of 259.41, MAE of 132.7, MAPE of 4.56 for the ANFIS-GA model; RSME of 295.26, MAE of 149.58, and MAPE of 6.98 for the ANFIS model, respectively. The results indicate that the ANFIS-GA model emulates the power output with better precision, thus providing a valuable planning tool to predict photovoltaic system behavior.