A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications

Mahyar Khosravi, Saeed Heshmatian, Davood A. Khaburi, Cristian Garcia, Jose Rodriguez

Resultado de la investigación: Conference contribution

3 Citas (Scopus)

Resumen

In this paper, a novel hybrid Maximum Power Point Tracking (MPPT) strategy has been proposed. This algorithm employs an idea similar to the Fractional Short Circuit Current (FSCC) method in order to improve the performance of the conventional Perturbation and Observation (P&O) algorithm. It should be considered that in the conventional FSCC method, the short circuit current needs to be measured at different time instances and hence, the power generated by PV module is not permanently delivered to the load. In the proposed strategy, a model of the PV cell is obtained based on a Multi-Layer Perceptron (MLP) structure. Then, the PV short circuit current is easily approximated using this model and is employed as an auxiliary information for the conventional P&O algorithm in order to simultaneously achieve fast and accurate tracking performance. The output of the proposed algorithm is the reference current value which is then fed to a predictive controller used to control the DC-DC boost converter placed between the PV cell and the load. Finally, the system is simulated in the MATLAB/Simulink environment. The simulation results verify the appropriate performance of the proposed method.

Idioma originalEnglish
Título de la publicación alojadaProceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-6
Número de páginas6
Volumen2018-January
ISBN (versión digital)9781509064250
DOI
EstadoPublished - 6 abr 2018
Evento2017 IEEE Southern Power Electronics Conference, SPEC 2017 - Puerto Varas, Chile
Duración: 4 dic 20177 dic 2017

Conference

Conference2017 IEEE Southern Power Electronics Conference, SPEC 2017
PaísChile
CiudadPuerto Varas
Período4/12/177/12/17

Huella dactilar

Short circuit currents
Neural networks
DC-DC converters
Multilayer neural networks
MATLAB
Controllers

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Energy Engineering and Power Technology

Citar esto

Khosravi, M., Heshmatian, S., Khaburi, D. A., Garcia, C., & Rodriguez, J. (2018). A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications. En Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017 (Vol. 2018-January, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPEC.2017.8333579
Khosravi, Mahyar ; Heshmatian, Saeed ; Khaburi, Davood A. ; Garcia, Cristian ; Rodriguez, Jose. / A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications. Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{8993c2e1b4704bab8f9f54957b0c4335,
title = "A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications",
abstract = "In this paper, a novel hybrid Maximum Power Point Tracking (MPPT) strategy has been proposed. This algorithm employs an idea similar to the Fractional Short Circuit Current (FSCC) method in order to improve the performance of the conventional Perturbation and Observation (P&O) algorithm. It should be considered that in the conventional FSCC method, the short circuit current needs to be measured at different time instances and hence, the power generated by PV module is not permanently delivered to the load. In the proposed strategy, a model of the PV cell is obtained based on a Multi-Layer Perceptron (MLP) structure. Then, the PV short circuit current is easily approximated using this model and is employed as an auxiliary information for the conventional P&O algorithm in order to simultaneously achieve fast and accurate tracking performance. The output of the proposed algorithm is the reference current value which is then fed to a predictive controller used to control the DC-DC boost converter placed between the PV cell and the load. Finally, the system is simulated in the MATLAB/Simulink environment. The simulation results verify the appropriate performance of the proposed method.",
keywords = "Maximum Power Tracking (MPPT), Model Predictive control (MPC), Multi-Layer Perceptron (MLP), Perturbation and Observation (P&O) Method, Solar Cell",
author = "Mahyar Khosravi and Saeed Heshmatian and Khaburi, {Davood A.} and Cristian Garcia and Jose Rodriguez",
year = "2018",
month = "4",
day = "6",
doi = "10.1109/SPEC.2017.8333579",
language = "English",
volume = "2018-January",
pages = "1--6",
booktitle = "Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Khosravi, M, Heshmatian, S, Khaburi, DA, Garcia, C & Rodriguez, J 2018, A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications. En Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2017 IEEE Southern Power Electronics Conference, SPEC 2017, Puerto Varas, Chile, 4/12/17. https://doi.org/10.1109/SPEC.2017.8333579

A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications. / Khosravi, Mahyar; Heshmatian, Saeed; Khaburi, Davood A.; Garcia, Cristian; Rodriguez, Jose.

Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

Resultado de la investigación: Conference contribution

TY - GEN

T1 - A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications

AU - Khosravi, Mahyar

AU - Heshmatian, Saeed

AU - Khaburi, Davood A.

AU - Garcia, Cristian

AU - Rodriguez, Jose

PY - 2018/4/6

Y1 - 2018/4/6

N2 - In this paper, a novel hybrid Maximum Power Point Tracking (MPPT) strategy has been proposed. This algorithm employs an idea similar to the Fractional Short Circuit Current (FSCC) method in order to improve the performance of the conventional Perturbation and Observation (P&O) algorithm. It should be considered that in the conventional FSCC method, the short circuit current needs to be measured at different time instances and hence, the power generated by PV module is not permanently delivered to the load. In the proposed strategy, a model of the PV cell is obtained based on a Multi-Layer Perceptron (MLP) structure. Then, the PV short circuit current is easily approximated using this model and is employed as an auxiliary information for the conventional P&O algorithm in order to simultaneously achieve fast and accurate tracking performance. The output of the proposed algorithm is the reference current value which is then fed to a predictive controller used to control the DC-DC boost converter placed between the PV cell and the load. Finally, the system is simulated in the MATLAB/Simulink environment. The simulation results verify the appropriate performance of the proposed method.

AB - In this paper, a novel hybrid Maximum Power Point Tracking (MPPT) strategy has been proposed. This algorithm employs an idea similar to the Fractional Short Circuit Current (FSCC) method in order to improve the performance of the conventional Perturbation and Observation (P&O) algorithm. It should be considered that in the conventional FSCC method, the short circuit current needs to be measured at different time instances and hence, the power generated by PV module is not permanently delivered to the load. In the proposed strategy, a model of the PV cell is obtained based on a Multi-Layer Perceptron (MLP) structure. Then, the PV short circuit current is easily approximated using this model and is employed as an auxiliary information for the conventional P&O algorithm in order to simultaneously achieve fast and accurate tracking performance. The output of the proposed algorithm is the reference current value which is then fed to a predictive controller used to control the DC-DC boost converter placed between the PV cell and the load. Finally, the system is simulated in the MATLAB/Simulink environment. The simulation results verify the appropriate performance of the proposed method.

KW - Maximum Power Tracking (MPPT)

KW - Model Predictive control (MPC)

KW - Multi-Layer Perceptron (MLP)

KW - Perturbation and Observation (P&O) Method

KW - Solar Cell

UR - http://www.scopus.com/inward/record.url?scp=85049220150&partnerID=8YFLogxK

U2 - 10.1109/SPEC.2017.8333579

DO - 10.1109/SPEC.2017.8333579

M3 - Conference contribution

VL - 2018-January

SP - 1

EP - 6

BT - Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Khosravi M, Heshmatian S, Khaburi DA, Garcia C, Rodriguez J. A novel hybrid model-based MPPT algorithm based on artificial neural networks for photovoltaic applications. En Proceedings - 2017 IEEE Southern Power Electronics Conference, SPEC 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/SPEC.2017.8333579