Resumen

YAJURE RAMIREZ, CÉSAR ARISTÓTELES. Evaluation of the quality of the electrical energy supplied by a grid-connected solar photovoltaic plant using machine learning and data mining algorithms. Ing. Desarro. [online]. 2025, vol.43, n.1, pp.44-63.  Epub 03-Ene-2025. ISSN 0122-3461.  https://doi.org/10.14482/inde.43.01.489.326.

The presence of photovoltaic solar plants to produce electricity implies the reduction of the use of fossil fuels, and of polluting emissions. The availability of solar energy depends on weather conditions, so the parameters of the electrical energy to be delivered could be affected. The objective of this research is to present a methodology based on data science for the evaluation of the energy quality of photovoltaic solar plants connected to the grid, considering current standards. It is applied to a 260 kWp plant of the National Institute of Standards and Technology of the United States. The parameters used are total harmonic distortion, voltage fluctuations and unbalance, electrical frequency, and power factor. Almost l00% of the records comply with the limits established by the standards for the parameters, except for power factor, with 63.56%. From the power factor classification model, the knowledge that apparent and active power, and frequency, are the most important variables was gathered. From the subgroup discovery algorithm, that solar irradiance appears in 40% of the subgroups, and frequency in 50%.

Palabras clave : electrical frequency; harmonic distortion; importance level; power factor; subgrupos. subgroups.

        · resumen en Español     · texto en Español     · Español ( pdf )