On the Estimation of Energy Production in PV Plants. A Comparative Study of Methodologies

Cortes-Carmona, Marcelo, Trigo-González, Mauricio, Batlles, Francisco Javier, Ferrada, Pablo, Acosta, Juan C., Alonso-Montecinos, Joaquín

ISES Solar World Congress 2019 · Santiago, Chile · 2019-11-04
Published by International Solar Energy Society (ISES)
DOI: 10.18086/swc.2019.14.03

Abstract

Nowadays it is inevitable to face the energy development of electrical systems without including solar energy. Considering the important participation that PV plants will have, which can affect the safety of electrical systems, it is necessary to develop methodologies that allow to predict and estimate adequately the production of photovoltaic plants. This research analyzes the performance of three methodologies that are commonly used in energy production estimation of PV plants; Multiple Linear Regression, Artificial Neural Networks and Vector Support Machines. The results show that there is a tradeoff between the type of problem, amount of data and computational resources used by the algorithms.

Download full text (PDF)

← All proceedings papers