Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data

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...

Full description

Bibliographic Details
Main Authors: Byung-ki Jeon, Eui-Jong Kim
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Energies
Subjects:
solar irradiance
long short-term memory
weather prediction
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

Similar Items