Investigating photovoltaic solar power output forecasting using machine learning algorithms
Solar power integration in electrical grids is complicated due to dependence on volatile weather conditions. To address this issue, continuous research and development is required to determine the best machine learning (ML) algorithm for PV solar power output forecasting. Existing studies have estab...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Taylor and Francis Ltd.
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-27102 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-271022023-05-29T17:39:34Z Investigating photovoltaic solar power output forecasting using machine learning algorithms Essam Y. Ahmed A.N. Ramli R. Chau K.-W. Idris Ibrahim M.S. Sherif M. Sefelnasr A. El-Shafie A. 57203146903 57214837520 56212747600 7202674661 57735870800 7005414714 6505592467 16068189400 Solar power integration in electrical grids is complicated due to dependence on volatile weather conditions. To address this issue, continuous research and development is required to determine the best machine learning (ML) algorithm for PV solar power output forecasting. Existing studies have established the superiority of the artificial neural network (ANN) and random forest (RF) algorithms in this field. However, more recent studies have demonstrated promising PV solar power output forecasting performances by the decision tree (DT), extreme gradient boosting (XGB), and long short-term memory (LSTM) algorithms. Therefore, the present study aims to address a research gap in this field by determining the best performer among these 5 algorithms. A data set from the United States� National Renewable Energy Laboratory (NREL) consisting of weather parameters and solar power output data for a monocrystalline silicon PV module in Cocoa, Florida was utilized. Comparisons of forecasting scores show that the ANN algorithm is superior as the ANN16 model produces the best mean absolute error (MAE), root mean squared error (RMSE) and coefficient of determination (R 2) with values of 0.4693, 0.8816 W, and 0.9988, respectively. It is concluded that ANN is the most reliable and applicable algorithm for PV solar power output forecasting. � 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. Final 2023-05-29T09:39:34Z 2023-05-29T09:39:34Z 2022 Article 10.1080/19942060.2022.2126528 2-s2.0-85139112710 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139112710&doi=10.1080%2f19942060.2022.2126528&partnerID=40&md5=c286adff731a5ea10e38429a85941579 https://irepository.uniten.edu.my/handle/123456789/27102 16 1 2002 2034 All Open Access, Gold Taylor and Francis Ltd. Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Solar power integration in electrical grids is complicated due to dependence on volatile weather conditions. To address this issue, continuous research and development is required to determine the best machine learning (ML) algorithm for PV solar power output forecasting. Existing studies have established the superiority of the artificial neural network (ANN) and random forest (RF) algorithms in this field. However, more recent studies have demonstrated promising PV solar power output forecasting performances by the decision tree (DT), extreme gradient boosting (XGB), and long short-term memory (LSTM) algorithms. Therefore, the present study aims to address a research gap in this field by determining the best performer among these 5 algorithms. A data set from the United States� National Renewable Energy Laboratory (NREL) consisting of weather parameters and solar power output data for a monocrystalline silicon PV module in Cocoa, Florida was utilized. Comparisons of forecasting scores show that the ANN algorithm is superior as the ANN16 model produces the best mean absolute error (MAE), root mean squared error (RMSE) and coefficient of determination (R 2) with values of 0.4693, 0.8816 W, and 0.9988, respectively. It is concluded that ANN is the most reliable and applicable algorithm for PV solar power output forecasting. � 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. |
| author2 |
57203146903 |
| author_facet |
57203146903 Essam Y. Ahmed A.N. Ramli R. Chau K.-W. Idris Ibrahim M.S. Sherif M. Sefelnasr A. El-Shafie A. |
| format |
Article |
| author |
Essam Y. Ahmed A.N. Ramli R. Chau K.-W. Idris Ibrahim M.S. Sherif M. Sefelnasr A. El-Shafie A. |
| spellingShingle |
Essam Y. Ahmed A.N. Ramli R. Chau K.-W. Idris Ibrahim M.S. Sherif M. Sefelnasr A. El-Shafie A. Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| author_sort |
Essam Y. |
| title |
Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| title_short |
Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| title_full |
Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| title_fullStr |
Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| title_full_unstemmed |
Investigating photovoltaic solar power output forecasting using machine learning algorithms |
| title_sort |
investigating photovoltaic solar power output forecasting using machine learning algorithms |
| publisher |
Taylor and Francis Ltd. |
| publishDate |
2023 |
| _version_ |
1806427570580750336 |
| score |
13.222552 |