Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method
Solar photovoltaic (PV) power generation is prone to drastic changes due to cloud cover. The power is easily affected within a very short period of time. Thus, the accuracy of grasping cloud distribution is important for PV power forecasting. This study proposes a novel sky image method to obtain th...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/13/4779 |
_version_ | 1797480218352418816 |
---|---|
author | Wen-Chi Kuo Chiun-Hsun Chen Sih-Yu Chen Chi-Chuan Wang |
author_facet | Wen-Chi Kuo Chiun-Hsun Chen Sih-Yu Chen Chi-Chuan Wang |
author_sort | Wen-Chi Kuo |
collection | DOAJ |
description | Solar photovoltaic (PV) power generation is prone to drastic changes due to cloud cover. The power is easily affected within a very short period of time. Thus, the accuracy of grasping cloud distribution is important for PV power forecasting. This study proposes a novel sky image method to obtain the cloud coverage rate used for short-term PV power forecasting. The authors developed an image analysis algorithm from the sky images obtained by an on-site whole sky imager (WSI). To verify the effectiveness of cloud coverage rate as the parameter for PV power forecast, four different combinations of weather features were used to compare the accuracy of short-term PV power forecasting. In addition to the artificial neural network (ANN) model, long short-term memory (LSTM) and the gated recurrent unit (GRU) were also introduced to compare their applicability conditions. After a comprehensive analysis, the coverage rate is the key weather feature, which can improve the accuracy by about 2% compared to the case without coverage feature. It also indicates that the LSTM and GRU models revealed better forecast results under different weather conditions, meaning that the cloud coverage rate proposed in this study has a significant benefit for short-term PV power forecasting. |
first_indexed | 2024-03-09T21:56:56Z |
format | Article |
id | doaj.art-9e471273514249f695294a1763fc908e |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-09T21:56:56Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-9e471273514249f695294a1763fc908e2023-11-23T19:57:11ZengMDPI AGEnergies1996-10732022-06-011513477910.3390/en15134779Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image MethodWen-Chi Kuo0Chiun-Hsun Chen1Sih-Yu Chen2Chi-Chuan Wang3Department of Mechanical Engineering, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanDepartment of Aerospace and Systems Engineering, Feng Chia University, Taichung 407, TaiwanDepartment of Mechanical Engineering, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanDepartment of Mechanical Engineering, National Yang Ming Chiao Tung University, Hsinchu 300, TaiwanSolar photovoltaic (PV) power generation is prone to drastic changes due to cloud cover. The power is easily affected within a very short period of time. Thus, the accuracy of grasping cloud distribution is important for PV power forecasting. This study proposes a novel sky image method to obtain the cloud coverage rate used for short-term PV power forecasting. The authors developed an image analysis algorithm from the sky images obtained by an on-site whole sky imager (WSI). To verify the effectiveness of cloud coverage rate as the parameter for PV power forecast, four different combinations of weather features were used to compare the accuracy of short-term PV power forecasting. In addition to the artificial neural network (ANN) model, long short-term memory (LSTM) and the gated recurrent unit (GRU) were also introduced to compare their applicability conditions. After a comprehensive analysis, the coverage rate is the key weather feature, which can improve the accuracy by about 2% compared to the case without coverage feature. It also indicates that the LSTM and GRU models revealed better forecast results under different weather conditions, meaning that the cloud coverage rate proposed in this study has a significant benefit for short-term PV power forecasting.https://www.mdpi.com/1996-1073/15/13/4779deep learning (DL)forecastingneural networkrenewable energysolar power generationsky image |
spellingShingle | Wen-Chi Kuo Chiun-Hsun Chen Sih-Yu Chen Chi-Chuan Wang Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method Energies deep learning (DL) forecasting neural network renewable energy solar power generation sky image |
title | Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method |
title_full | Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method |
title_fullStr | Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method |
title_full_unstemmed | Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method |
title_short | Deep Learning Neural Networks for Short-Term PV Power Forecasting via Sky Image Method |
title_sort | deep learning neural networks for short term pv power forecasting via sky image method |
topic | deep learning (DL) forecasting neural network renewable energy solar power generation sky image |
url | https://www.mdpi.com/1996-1073/15/13/4779 |
work_keys_str_mv | AT wenchikuo deeplearningneuralnetworksforshorttermpvpowerforecastingviaskyimagemethod AT chiunhsunchen deeplearningneuralnetworksforshorttermpvpowerforecastingviaskyimagemethod AT sihyuchen deeplearningneuralnetworksforshorttermpvpowerforecastingviaskyimagemethod AT chichuanwang deeplearningneuralnetworksforshorttermpvpowerforecastingviaskyimagemethod |