Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction
This paper presents an assessment for the artificial neural network (ANN) based approach for hourly solar radiation prediction. The Four ANNs topologies were used including a generalized (GRNN), a feed-forward backpropagation (FFNN), a cascade-forward backpropagation (CFNN), and an Elman backpropaga...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2012-01-01
|
| Series: | International Journal of Photoenergy |
| Online Access: | http://dx.doi.org/10.1155/2012/946890 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549266354077696 |
|---|---|
| author | Tamer Khatib Azah Mohamed K. Sopian M. Mahmoud |
| author_facet | Tamer Khatib Azah Mohamed K. Sopian M. Mahmoud |
| author_sort | Tamer Khatib |
| collection | DOAJ |
| description | This paper presents an assessment for the artificial neural network (ANN) based approach for hourly solar radiation prediction. The Four ANNs topologies were used including a generalized (GRNN), a feed-forward backpropagation (FFNN), a cascade-forward backpropagation (CFNN), and an Elman backpropagation (ELMNN). The three statistical values used to evaluate the efficacy of the neural networks were mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Prediction results show that the GRNN exceeds the other proposed methods. The average values of the MAPE, MBE and RMSE using GRNN were 4.9%, 0.29% and 5.75%, respectively. FFNN and CFNN efficacies were acceptable in general, but their predictive value was degraded in poor solar radiation conditions. The average values of the MAPE, MBE and RMSE using the FFNN were 23%, −.09% and 21.9%, respectively, while the average values of the MAPE, MBE and RMSE using CFNN were 22.5%, −19.15% and 21.9%, respectively. ELMNN fared the worst among the proposed methods in predicting hourly solar radiation with average MABE, MBE and RMSE values of 34.5%, −11.1% and 34.35%. The use of the GRNN to predict solar radiation in all climate conditions yielded results that were highly accurate and efficient. |
| format | Article |
| id | doaj-art-d300c13deabf487692e0cecc78cebca0 |
| institution | Kabale University |
| issn | 1110-662X 1687-529X |
| language | English |
| publishDate | 2012-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Photoenergy |
| spelling | doaj-art-d300c13deabf487692e0cecc78cebca02025-02-03T06:11:46ZengWileyInternational Journal of Photoenergy1110-662X1687-529X2012-01-01201210.1155/2012/946890946890Assessment of Artificial Neural Networks for Hourly Solar Radiation PredictionTamer Khatib0Azah Mohamed1K. Sopian2M. Mahmoud3Department of Electrical, Electronic and System Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Selangor, Bangi 43600, MalaysiaDepartment of Electrical, Electronic and System Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Selangor, Bangi 43600, MalaysiaSolar Energy Research Institute, Universiti Kebangsaan Malaysia, Selangor, Bangi 43600, MalaysiaDepartment of Electrical Engineering, Engineering Faculty, An-Najah National University, Nablus 97300, PalestineThis paper presents an assessment for the artificial neural network (ANN) based approach for hourly solar radiation prediction. The Four ANNs topologies were used including a generalized (GRNN), a feed-forward backpropagation (FFNN), a cascade-forward backpropagation (CFNN), and an Elman backpropagation (ELMNN). The three statistical values used to evaluate the efficacy of the neural networks were mean absolute percentage error (MAPE), mean bias error (MBE) and root mean square error (RMSE). Prediction results show that the GRNN exceeds the other proposed methods. The average values of the MAPE, MBE and RMSE using GRNN were 4.9%, 0.29% and 5.75%, respectively. FFNN and CFNN efficacies were acceptable in general, but their predictive value was degraded in poor solar radiation conditions. The average values of the MAPE, MBE and RMSE using the FFNN were 23%, −.09% and 21.9%, respectively, while the average values of the MAPE, MBE and RMSE using CFNN were 22.5%, −19.15% and 21.9%, respectively. ELMNN fared the worst among the proposed methods in predicting hourly solar radiation with average MABE, MBE and RMSE values of 34.5%, −11.1% and 34.35%. The use of the GRNN to predict solar radiation in all climate conditions yielded results that were highly accurate and efficient.http://dx.doi.org/10.1155/2012/946890 |
| spellingShingle | Tamer Khatib Azah Mohamed K. Sopian M. Mahmoud Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction International Journal of Photoenergy |
| title | Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction |
| title_full | Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction |
| title_fullStr | Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction |
| title_full_unstemmed | Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction |
| title_short | Assessment of Artificial Neural Networks for Hourly Solar Radiation Prediction |
| title_sort | assessment of artificial neural networks for hourly solar radiation prediction |
| url | http://dx.doi.org/10.1155/2012/946890 |
| work_keys_str_mv | AT tamerkhatib assessmentofartificialneuralnetworksforhourlysolarradiationprediction AT azahmohamed assessmentofartificialneuralnetworksforhourlysolarradiationprediction AT ksopian assessmentofartificialneuralnetworksforhourlysolarradiationprediction AT mmahmoud assessmentofartificialneuralnetworksforhourlysolarradiationprediction |