Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data
Solar irradiance prediction is significant for maximizing energy-saving effects in the predictive control of buildings. Several models for solar irradiance prediction have been developed; however, they require the collection of weather data over a long period in the predicted target region or evalua...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/20/5258 |
id |
doaj-a984ddbd6c714303a45661bceb4d079f |
---|---|
record_format |
Article |
spelling |
doaj-a984ddbd6c714303a45661bceb4d079f2020-11-25T03:55:46ZengMDPI AGEnergies1996-10732020-10-01135258525810.3390/en13205258Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local DataByung-ki Jeon0Eui-Jong Kim1Department of Architectural Engineering, Inha University, Incheon 22212, KoreaDepartment of Architectural Engineering, Inha University, Incheon 22212, KoreaSolar irradiance prediction is significant for maximizing energy-saving effects in the predictive control of buildings. Several models for solar irradiance prediction have been developed; however, they require the collection of weather data over a long period in the predicted target region or evaluation of various weather data in real time. In this study, a long short-term memory algorithm–based model is proposed using limited input data and data from other regions. The proposed model can predict solar irradiance using next-day weather forecasts by the Korea Meteorological Administration and daily solar irradiance, and it is possible to build a model with one-time learning using national and international data. The model developed in this study showed excellent predictive performance with a coefficient of variation of the root mean square error of 12% per year even if the learning and forecast regions were different, assuming that the weather forecast was correct.https://www.mdpi.com/1996-1073/13/20/5258solar irradiancelong short-term memoryweather prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Byung-ki Jeon Eui-Jong Kim |
spellingShingle |
Byung-ki Jeon Eui-Jong Kim Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data Energies solar irradiance long short-term memory weather prediction |
author_facet |
Byung-ki Jeon Eui-Jong Kim |
author_sort |
Byung-ki Jeon |
title |
Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data |
title_short |
Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data |
title_full |
Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data |
title_fullStr |
Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data |
title_full_unstemmed |
Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data |
title_sort |
next-day prediction of hourly solar irradiance using local weather forecasts and lstm trained with non-local data |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2020-10-01 |
description |
Solar irradiance prediction is significant for maximizing energy-saving effects in the predictive control of buildings. Several models for solar irradiance prediction have been developed; however, they require the collection of weather data over a long period in the predicted target region or evaluation of various weather data in real time. In this study, a long short-term memory algorithm–based model is proposed using limited input data and data from other regions. The proposed model can predict solar irradiance using next-day weather forecasts by the Korea Meteorological Administration and daily solar irradiance, and it is possible to build a model with one-time learning using national and international data. The model developed in this study showed excellent predictive performance with a coefficient of variation of the root mean square error of 12% per year even if the learning and forecast regions were different, assuming that the weather forecast was correct. |
topic |
solar irradiance long short-term memory weather prediction |
url |
https://www.mdpi.com/1996-1073/13/20/5258 |
work_keys_str_mv |
AT byungkijeon nextdaypredictionofhourlysolarirradianceusinglocalweatherforecastsandlstmtrainedwithnonlocaldata AT euijongkim nextdaypredictionofhourlysolarirradianceusinglocalweatherforecastsandlstmtrainedwithnonlocaldata |
_version_ |
1724468245896888320 |