Sensitivity of artificial neural network based model for photovoltaic system actual performance

Ammar Mohammed Ameen, Jagadeesh Pasupuleti, Tamer Khatib

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A novel prediction model for the output current of PV module is proposed in this paper. The proposed model is based on cascade-forward back propagation artificial neural network with two inputs and one output. Solar radiation and ambient temperature are the inputs and the predicted current is the output. Experiment data for a 1.4 kWp PV systems installed in Sohar city, Oman are utilized in developing the proposed model. These data has an interval of 2 seconds in order to consider the uncertainty of the system's output current. In order to evaluate the accuracy of the neural network, three statistical values are used namely mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. The results show that the MAPE, MBE and RMSE of the proposed model are 7.08%, -4.98% and 7.8%, respectively

Original languageEnglish
Title of host publicationConference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014
EditorsMohd Izhwan Muhamad, Mohammad Nawawi Seroji
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages241-244
Number of pages4
ISBN (Electronic)9781479972975
DOIs
Publication statusPublished - 17 Mar 2014
Event2014 IEEE International Conference on Power and Energy, PECon 2014 - Kuching, Sarawak, Malaysia
Duration: 01 Dec 201403 Dec 2014

Publication series

NameConference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014

Other

Other2014 IEEE International Conference on Power and Energy, PECon 2014
CountryMalaysia
CityKuching, Sarawak
Period01/12/1403/12/14

Fingerprint

Neural networks
Mean square error
Solar radiation
Backpropagation
Experiments
Temperature
Uncertainty

All Science Journal Classification (ASJC) codes

  • Fuel Technology
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Ameen, A. M., Pasupuleti, J., & Khatib, T. (2014). Sensitivity of artificial neural network based model for photovoltaic system actual performance. In M. I. Muhamad, & M. N. Seroji (Eds.), Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014 (pp. 241-244). [7062449] (Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PECON.2014.7062449
Ameen, Ammar Mohammed ; Pasupuleti, Jagadeesh ; Khatib, Tamer. / Sensitivity of artificial neural network based model for photovoltaic system actual performance. Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014. editor / Mohd Izhwan Muhamad ; Mohammad Nawawi Seroji. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 241-244 (Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014).
@inproceedings{9358269459e74cccb97dbf8b3d140e67,
title = "Sensitivity of artificial neural network based model for photovoltaic system actual performance",
abstract = "A novel prediction model for the output current of PV module is proposed in this paper. The proposed model is based on cascade-forward back propagation artificial neural network with two inputs and one output. Solar radiation and ambient temperature are the inputs and the predicted current is the output. Experiment data for a 1.4 kWp PV systems installed in Sohar city, Oman are utilized in developing the proposed model. These data has an interval of 2 seconds in order to consider the uncertainty of the system's output current. In order to evaluate the accuracy of the neural network, three statistical values are used namely mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. The results show that the MAPE, MBE and RMSE of the proposed model are 7.08{\%}, -4.98{\%} and 7.8{\%}, respectively",
author = "Ameen, {Ammar Mohammed} and Jagadeesh Pasupuleti and Tamer Khatib",
year = "2014",
month = "3",
day = "17",
doi = "10.1109/PECON.2014.7062449",
language = "English",
series = "Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "241--244",
editor = "Muhamad, {Mohd Izhwan} and Seroji, {Mohammad Nawawi}",
booktitle = "Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014",
address = "United States",

}

Ameen, AM, Pasupuleti, J & Khatib, T 2014, Sensitivity of artificial neural network based model for photovoltaic system actual performance. in MI Muhamad & MN Seroji (eds), Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014., 7062449, Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014, Institute of Electrical and Electronics Engineers Inc., pp. 241-244, 2014 IEEE International Conference on Power and Energy, PECon 2014, Kuching, Sarawak, Malaysia, 01/12/14. https://doi.org/10.1109/PECON.2014.7062449

Sensitivity of artificial neural network based model for photovoltaic system actual performance. / Ameen, Ammar Mohammed; Pasupuleti, Jagadeesh; Khatib, Tamer.

Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014. ed. / Mohd Izhwan Muhamad; Mohammad Nawawi Seroji. Institute of Electrical and Electronics Engineers Inc., 2014. p. 241-244 7062449 (Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Sensitivity of artificial neural network based model for photovoltaic system actual performance

AU - Ameen, Ammar Mohammed

AU - Pasupuleti, Jagadeesh

AU - Khatib, Tamer

PY - 2014/3/17

Y1 - 2014/3/17

N2 - A novel prediction model for the output current of PV module is proposed in this paper. The proposed model is based on cascade-forward back propagation artificial neural network with two inputs and one output. Solar radiation and ambient temperature are the inputs and the predicted current is the output. Experiment data for a 1.4 kWp PV systems installed in Sohar city, Oman are utilized in developing the proposed model. These data has an interval of 2 seconds in order to consider the uncertainty of the system's output current. In order to evaluate the accuracy of the neural network, three statistical values are used namely mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. The results show that the MAPE, MBE and RMSE of the proposed model are 7.08%, -4.98% and 7.8%, respectively

AB - A novel prediction model for the output current of PV module is proposed in this paper. The proposed model is based on cascade-forward back propagation artificial neural network with two inputs and one output. Solar radiation and ambient temperature are the inputs and the predicted current is the output. Experiment data for a 1.4 kWp PV systems installed in Sohar city, Oman are utilized in developing the proposed model. These data has an interval of 2 seconds in order to consider the uncertainty of the system's output current. In order to evaluate the accuracy of the neural network, three statistical values are used namely mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. The results show that the MAPE, MBE and RMSE of the proposed model are 7.08%, -4.98% and 7.8%, respectively

UR - http://www.scopus.com/inward/record.url?scp=84946691724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946691724&partnerID=8YFLogxK

U2 - 10.1109/PECON.2014.7062449

DO - 10.1109/PECON.2014.7062449

M3 - Conference contribution

AN - SCOPUS:84946691724

T3 - Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014

SP - 241

EP - 244

BT - Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014

A2 - Muhamad, Mohd Izhwan

A2 - Seroji, Mohammad Nawawi

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ameen AM, Pasupuleti J, Khatib T. Sensitivity of artificial neural network based model for photovoltaic system actual performance. In Muhamad MI, Seroji MN, editors, Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 241-244. 7062449. (Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014). https://doi.org/10.1109/PECON.2014.7062449