Solar Photovoltaic Forecasting of Power Output Using LSTM Networks
The penetration of renewable energies has increased during the last decades since it has become an effective solution to the world’s energy challenges. Among all renewable energy sources, photovoltaic (PV) technology is the most immediate way to convert solar radiation into electricity. Nevertheless...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Atmosphere |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4433/12/1/124 |
id |
doaj-dc4c4f4d8bdf47c999cc24e158948a9c |
---|---|
record_format |
Article |
spelling |
doaj-dc4c4f4d8bdf47c999cc24e158948a9c2021-01-19T00:02:10ZengMDPI AGAtmosphere2073-44332021-01-011212412410.3390/atmos12010124Solar Photovoltaic Forecasting of Power Output Using LSTM NetworksMaria Konstantinou0Stefani Peratikou1Alexandros G. Charalambides2Department of Chemical Engineering, Cyprus University of Technology, Corner of Athinon and Anexartisias, 57, Lemesos 3603, CyprusDepartment of Chemical Engineering, Cyprus University of Technology, Corner of Athinon and Anexartisias, 57, Lemesos 3603, CyprusDepartment of Chemical Engineering, Cyprus University of Technology, Corner of Athinon and Anexartisias, 57, Lemesos 3603, CyprusThe penetration of renewable energies has increased during the last decades since it has become an effective solution to the world’s energy challenges. Among all renewable energy sources, photovoltaic (PV) technology is the most immediate way to convert solar radiation into electricity. Nevertheless, PV power output is affected by several factors, such as location, clouds, etc. As PV plants proliferate and represent significant contributors to grid electricity production, it becomes increasingly important to manage their inherent alterability. Therefore, solar PV forecasting is a pivotal factor to support reliable and cost-effective grid operation and control. In this paper, a stacked long short-term memory network, which is a significant component of the deep recurrent neural network, is considered for the prediction of PV power output for 1.5 h ahead. Historical data of PV power output from a PV plant in Nicosia, Cyprus, were used as input to the forecasting model. Once the model was defined and trained, the model performance was assessed qualitative (by graphical tools) and quantitative (by calculating the Root Mean Square Error (RMSE) and by applying the k-fold cross-validation method). The results showed that our model can predict well, since the RMSE gives a value of 0.11368, whereas when applying the k-fold cross-validation, the mean of the resulting RMSE values is 0.09394 with a standard deviation 0.01616.https://www.mdpi.com/2073-4433/12/1/124solar energyclimate changephotovoltaic power forecastingmachine learningstacked LSTM network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Maria Konstantinou Stefani Peratikou Alexandros G. Charalambides |
spellingShingle |
Maria Konstantinou Stefani Peratikou Alexandros G. Charalambides Solar Photovoltaic Forecasting of Power Output Using LSTM Networks Atmosphere solar energy climate change photovoltaic power forecasting machine learning stacked LSTM network |
author_facet |
Maria Konstantinou Stefani Peratikou Alexandros G. Charalambides |
author_sort |
Maria Konstantinou |
title |
Solar Photovoltaic Forecasting of Power Output Using LSTM Networks |
title_short |
Solar Photovoltaic Forecasting of Power Output Using LSTM Networks |
title_full |
Solar Photovoltaic Forecasting of Power Output Using LSTM Networks |
title_fullStr |
Solar Photovoltaic Forecasting of Power Output Using LSTM Networks |
title_full_unstemmed |
Solar Photovoltaic Forecasting of Power Output Using LSTM Networks |
title_sort |
solar photovoltaic forecasting of power output using lstm networks |
publisher |
MDPI AG |
series |
Atmosphere |
issn |
2073-4433 |
publishDate |
2021-01-01 |
description |
The penetration of renewable energies has increased during the last decades since it has become an effective solution to the world’s energy challenges. Among all renewable energy sources, photovoltaic (PV) technology is the most immediate way to convert solar radiation into electricity. Nevertheless, PV power output is affected by several factors, such as location, clouds, etc. As PV plants proliferate and represent significant contributors to grid electricity production, it becomes increasingly important to manage their inherent alterability. Therefore, solar PV forecasting is a pivotal factor to support reliable and cost-effective grid operation and control. In this paper, a stacked long short-term memory network, which is a significant component of the deep recurrent neural network, is considered for the prediction of PV power output for 1.5 h ahead. Historical data of PV power output from a PV plant in Nicosia, Cyprus, were used as input to the forecasting model. Once the model was defined and trained, the model performance was assessed qualitative (by graphical tools) and quantitative (by calculating the Root Mean Square Error (RMSE) and by applying the k-fold cross-validation method). The results showed that our model can predict well, since the RMSE gives a value of 0.11368, whereas when applying the k-fold cross-validation, the mean of the resulting RMSE values is 0.09394 with a standard deviation 0.01616. |
topic |
solar energy climate change photovoltaic power forecasting machine learning stacked LSTM network |
url |
https://www.mdpi.com/2073-4433/12/1/124 |
work_keys_str_mv |
AT mariakonstantinou solarphotovoltaicforecastingofpoweroutputusinglstmnetworks AT stefaniperatikou solarphotovoltaicforecastingofpoweroutputusinglstmnetworks AT alexandrosgcharalambides solarphotovoltaicforecastingofpoweroutputusinglstmnetworks |
_version_ |
1724332772644880384 |