A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems
The integration of photovoltaic energy into a grid demands accurate power output forecasting. In this research, an hour ahead prediction of power output is performed on an annual basis over real data period (2016-2019) for three different PV systems based on polycrystalline, monocrystalline, and thi...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Published: |
Elsevier
2022
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/41479/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Malaya |
id |
my.um.eprints.41479 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.414792023-10-23T08:52:55Z http://eprints.um.edu.my/41479/ A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems Akhter, Muhammad Naveed Mekhilef, Saad Mokhlis, Hazlie Ali, Raza Usama, Muhammad Muhammad, Munir Azam Mohd Khairuddin, Anis Salwa TK Electrical engineering. Electronics Nuclear engineering The integration of photovoltaic energy into a grid demands accurate power output forecasting. In this research, an hour ahead prediction of power output is performed on an annual basis over real data period (2016-2019) for three different PV systems based on polycrystalline, monocrystalline, and thin-film technologies. The solar radiation, ambient temperature, module temperature and wind speed are the considered input parameters, while the power output of each PV system is the output parameter. A hybrid deep learning (DL) method (SSA-RNN-LSTM) is proposed for an hour ahead prediction of output power for each PV system. The proposed technique is compared with GA-RNN-LSTM, PSO-RNN-LSTM and RNN-LSTM. The considered forecasting accuracy measurement parameters are RMSE, MSE, MAE and coefficient of determination (R-2). The findings elaborate that SSA-RNN-LSTM has shown better forecasting accuracy with the lowest (RMSE and MSE), highest (R-2) and highest convergence speed compared to other methods. The proposed model has shown testing (RMSE and MAE) of (19.14% and 21.57%), (15.4% and 10.81%) and (22.9% and 25.2%) lower than RNN-LSTM for polycrystalline, monocrystalline and thin-film PV systems respectively. Furthermore, the proposed model is found more robust in predicting the power output for three different PV systems over four years data period. Elsevier 2022-02 Article PeerReviewed Akhter, Muhammad Naveed and Mekhilef, Saad and Mokhlis, Hazlie and Ali, Raza and Usama, Muhammad and Muhammad, Munir Azam and Mohd Khairuddin, Anis Salwa (2022) A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems. Applied Energy, 307. ISSN 0306-2619, DOI https://doi.org/10.1016/j.apenergy.2021.118185 <https://doi.org/10.1016/j.apenergy.2021.118185>. 10.1016/j.apenergy.2021.118185 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Akhter, Muhammad Naveed Mekhilef, Saad Mokhlis, Hazlie Ali, Raza Usama, Muhammad Muhammad, Munir Azam Mohd Khairuddin, Anis Salwa A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
description |
The integration of photovoltaic energy into a grid demands accurate power output forecasting. In this research, an hour ahead prediction of power output is performed on an annual basis over real data period (2016-2019) for three different PV systems based on polycrystalline, monocrystalline, and thin-film technologies. The solar radiation, ambient temperature, module temperature and wind speed are the considered input parameters, while the power output of each PV system is the output parameter. A hybrid deep learning (DL) method (SSA-RNN-LSTM) is proposed for an hour ahead prediction of output power for each PV system. The proposed technique is compared with GA-RNN-LSTM, PSO-RNN-LSTM and RNN-LSTM. The considered forecasting accuracy measurement parameters are RMSE, MSE, MAE and coefficient of determination (R-2). The findings elaborate that SSA-RNN-LSTM has shown better forecasting accuracy with the lowest (RMSE and MSE), highest (R-2) and highest convergence speed compared to other methods. The proposed model has shown testing (RMSE and MAE) of (19.14% and 21.57%), (15.4% and 10.81%) and (22.9% and 25.2%) lower than RNN-LSTM for polycrystalline, monocrystalline and thin-film PV systems respectively. Furthermore, the proposed model is found more robust in predicting the power output for three different PV systems over four years data period. |
format |
Article |
author |
Akhter, Muhammad Naveed Mekhilef, Saad Mokhlis, Hazlie Ali, Raza Usama, Muhammad Muhammad, Munir Azam Mohd Khairuddin, Anis Salwa |
author_facet |
Akhter, Muhammad Naveed Mekhilef, Saad Mokhlis, Hazlie Ali, Raza Usama, Muhammad Muhammad, Munir Azam Mohd Khairuddin, Anis Salwa |
author_sort |
Akhter, Muhammad Naveed |
title |
A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
title_short |
A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
title_full |
A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
title_fullStr |
A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
title_full_unstemmed |
A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
title_sort |
hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems |
publisher |
Elsevier |
publishDate |
2022 |
url |
http://eprints.um.edu.my/41479/ |
_version_ |
1781704538172948480 |