A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder

Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–d...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingfa Zi, Feiyi Liu, Mingyang Liu, Yang Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/10/2434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711817119498240
author Xingfa Zi
Feiyi Liu
Mingyang Liu
Yang Wang
author_facet Xingfa Zi
Feiyi Liu
Mingyang Liu
Yang Wang
author_sort Xingfa Zi
collection DOAJ
description Deep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–decoder model, to forecast PV power generation. TiDE compresses historical time series and covariates into latent representations via residual connections and reconstructs future values through a temporal decoder, capturing both long- and short-term dependencies. We trained the model using data from 2020 to 2022 from Australia’s Desert Knowledge Australia Solar Centre (DKASC), with 2023 data used for testing. Forecast accuracy was evaluated using the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> coefficient of determination, mean absolute error (MAE), and root mean square error (RMSE). In the 5 min ahead forecasting test, TiDE demonstrated high short-term accuracy with an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.952, MAE of 0.150, and RMSE of 0.349, though performance declines for longer horizons, such as the 1 h ahead forecast, compared to other algorithms. For one-day-ahead forecasts, it achieved an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.712, an MAE of 0.507, and an RMSE of 0.856, effectively capturing medium-term weather trends but showing limited responsiveness to sudden weather changes. Further analysis indicated improved performance in cloudy and rainy weather, and seasonal analysis reveals higher accuracy in spring and autumn, with reduced accuracy in summer and winter due to extreme conditions. Additionally, we explore the TiDE model’s sensitivity to input environmental variables, algorithmic versatility, and the implications of forecasting errors on PV grid integration. These findings highlight TiDE’s superior forecasting accuracy and robust adaptability across weather conditions, while also revealing its limitations under abrupt changes.
format Article
id doaj-art-32a09bf9df85468286af6e52a71d6d8d
institution DOAJ
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-32a09bf9df85468286af6e52a71d6d8d2025-08-20T03:14:31ZengMDPI AGEnergies1996-10732025-05-011810243410.3390/en18102434A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense EncoderXingfa Zi0Feiyi Liu1Mingyang Liu2Yang Wang3School of Physics, Electrical and Energy Engineering, Chuxiong Normal University, Chuxiong 675000, ChinaSchool of Physics, Electrical and Energy Engineering, Chuxiong Normal University, Chuxiong 675000, ChinaSchool of Physics, Electrical and Energy Engineering, Chuxiong Normal University, Chuxiong 675000, ChinaSchool of Big Data and Basic Science, Shandong Institute of Petroleum and Chemical Technology, Dongying 257061, ChinaDeep learning has become a widely used approach in photovoltaic (PV) power generation forecasting due to its strong self-learning and parameter optimization capabilities. In this study, we apply a deep learning algorithm, known as the time-series dense encoder (TiDE), which is an MLP-based encoder–decoder model, to forecast PV power generation. TiDE compresses historical time series and covariates into latent representations via residual connections and reconstructs future values through a temporal decoder, capturing both long- and short-term dependencies. We trained the model using data from 2020 to 2022 from Australia’s Desert Knowledge Australia Solar Centre (DKASC), with 2023 data used for testing. Forecast accuracy was evaluated using the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> coefficient of determination, mean absolute error (MAE), and root mean square error (RMSE). In the 5 min ahead forecasting test, TiDE demonstrated high short-term accuracy with an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.952, MAE of 0.150, and RMSE of 0.349, though performance declines for longer horizons, such as the 1 h ahead forecast, compared to other algorithms. For one-day-ahead forecasts, it achieved an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.712, an MAE of 0.507, and an RMSE of 0.856, effectively capturing medium-term weather trends but showing limited responsiveness to sudden weather changes. Further analysis indicated improved performance in cloudy and rainy weather, and seasonal analysis reveals higher accuracy in spring and autumn, with reduced accuracy in summer and winter due to extreme conditions. Additionally, we explore the TiDE model’s sensitivity to input environmental variables, algorithmic versatility, and the implications of forecasting errors on PV grid integration. These findings highlight TiDE’s superior forecasting accuracy and robust adaptability across weather conditions, while also revealing its limitations under abrupt changes.https://www.mdpi.com/1996-1073/18/10/2434photovoltaic energyrenewable energyPV power generation forecastingtime-series forecastingdeep learningtime-series dense encoder
spellingShingle Xingfa Zi
Feiyi Liu
Mingyang Liu
Yang Wang
A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
Energies
photovoltaic energy
renewable energy
PV power generation forecasting
time-series forecasting
deep learning
time-series dense encoder
title A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
title_full A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
title_fullStr A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
title_full_unstemmed A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
title_short A Deep Learning Method for Photovoltaic Power Generation Forecasting Based on a Time-Series Dense Encoder
title_sort deep learning method for photovoltaic power generation forecasting based on a time series dense encoder
topic photovoltaic energy
renewable energy
PV power generation forecasting
time-series forecasting
deep learning
time-series dense encoder
url https://www.mdpi.com/1996-1073/18/10/2434
work_keys_str_mv AT xingfazi adeeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT feiyiliu adeeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT mingyangliu adeeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT yangwang adeeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT xingfazi deeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT feiyiliu deeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT mingyangliu deeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder
AT yangwang deeplearningmethodforphotovoltaicpowergenerationforecastingbasedonatimeseriesdenseencoder