TY - CONF
T1 - Nonlinear loads determination using harmonic information in photovoltaic generation systems
AU - De DIos Fuentes, Juan
AU - Orjuela-Cañón, Alvaro D.
AU - Escobar, Héctor Iván Tangarife
N1 - Funding Information:
El análisis realizado al sistema fotovoltaico del SENA es un preámbulo para trabajos complementarios relacionados con el desarrollo de interfaces o de dispositivos de supervisión y registro de la señal eléctrica, también podría ser de gran ayuda para el personal encargado de realizar análisis y conexiones de las diferentes cargas que están siendo conectadas al sistema.
Funding Information:
RECONOCIMIENTOS Los autores agradecen a la Universidad Antonio Nariño que a través de su proyecto “Diseño e implementación de un sistema inteligente de gestión de recursos para una microrred abastecida por energías alternativas” con código 2017211, está financiando el tiempo para este tipo de iniciativas. Los autores agradecen también, al Servicio Nacional de Aprendizaje SENA por facilitar las instalaciones del sistema fotovoltáico para la investigación realizada y al centro Metalmecánico por permitir la participación de instructores en el proyecto.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/5
Y1 - 2018/10/5
N2 - This paper contains a proposal to determine the kind of nonlinear load when different appliances are connected to the solar generation system. A database built with sampled signals from the photovoltaic systems of the National Learning Service (SENA) in Bogota was employed. The methodology used information from harmonic distortion extracted from nonlinear loads, which was used as input in an artificial neural network with supervised learning. Two proposals were implemented. First one was based on energy information and second one was worked with wave peaks information. Results show that a classification rate of 95% could be reached in a problem with eight classes.
AB - This paper contains a proposal to determine the kind of nonlinear load when different appliances are connected to the solar generation system. A database built with sampled signals from the photovoltaic systems of the National Learning Service (SENA) in Bogota was employed. The methodology used information from harmonic distortion extracted from nonlinear loads, which was used as input in an artificial neural network with supervised learning. Two proposals were implemented. First one was based on energy information and second one was worked with wave peaks information. Results show that a classification rate of 95% could be reached in a problem with eight classes.
UR - http://www.scopus.com/inward/record.url?scp=85056445459&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056445459&partnerID=8YFLogxK
U2 - 10.1109/ColCACI.2018.8484851
DO - 10.1109/ColCACI.2018.8484851
M3 - Conference proceedings
AN - SCOPUS:85056445459
T2 - 1st IEEE Colombian Conference on Applications in Computational Intelligence, ColCACI 2018
Y2 - 16 May 2018 through 18 May 2018
ER -
