Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework

The variability in the spatiotemporal distribution of power generation is a significant challenge for accurately predicting renewable energy production patterns. Furthermore, numerous forms of unforeseen data contamination degrade the precision of forecasts since superfluous data points adversely af...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Shadman Abid, Razzaqul Ahshan, Mohammed Al-Abri, Rashid Al Abri
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:Energy Conversion and Management: X
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590174525000510
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850133552035790848
author Md. Shadman Abid
Razzaqul Ahshan
Mohammed Al-Abri
Rashid Al Abri
author_facet Md. Shadman Abid
Razzaqul Ahshan
Mohammed Al-Abri
Rashid Al Abri
author_sort Md. Shadman Abid
collection DOAJ
description The variability in the spatiotemporal distribution of power generation is a significant challenge for accurately predicting renewable energy production patterns. Furthermore, numerous forms of unforeseen data contamination degrade the precision of forecasts since superfluous data points adversely affect the regression model. In this context, a novel robust deep learning model, termed the Convolutional Neural Network-Bidirectional Long Short-Term Memory model with spatiotemporal attention mechanism (CNN-BiLSTM-STA), is developed in this study. The suggested model integrates the feature extraction expertise of CNNs with the sequence modeling proficiency of BiLSTM networks to capture spatial linkages and temporal interdependence adeptly. Moreover, the integrated spatiotemporal attention mechanism selectively focuses on significant spatial regions and time steps to enhance the prediction of spatiotemporal sequences of time-resolved grid data. The proposed architecture allows plant proprietors and system operators to obtain accurate predictions across extensive spatiotemporal patterns by eliminating the necessity for individual model fitting for each site/horizon or an additional data preprocessing phase before training. In addition, the Correntropy-based training criterion is employed to ensure the robustness of the recommended method against various types of data contamination, including data incompletion, Gaussian noises, outliers, and a mixed combination of disturbances. Furthermore, the Partial Reinforcement Optimization technique is applied to optimize the hyperparameters of the proposed model. The suggested framework incorporates numerous photovoltaic installations in Arizona and wind power installations in Texas to provide concurrent forecasts for multiple periods. The efficacy of the suggested forecasting model is evaluated by comparing it with three state-of-the-art methods. Numerical findings demonstrate that the proposed model surpasses other methods by successfully integrating spatial and temporal characteristics.
format Article
id doaj-art-eeeb21d978064e5da2a241db40d902fe
institution OA Journals
issn 2590-1745
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series Energy Conversion and Management: X
spelling doaj-art-eeeb21d978064e5da2a241db40d902fe2025-08-20T02:31:56ZengElsevierEnergy Conversion and Management: X2590-17452025-04-012610091910.1016/j.ecmx.2025.100919Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention FrameworkMd. Shadman Abid0Razzaqul Ahshan1Mohammed Al-Abri2Rashid Al Abri3Nanotechnology Research Center, Sultan Qaboos University, Al-Khoud, 123, OmanDepartment of Electrical and Computer Engineering, College of Engineering, Sultan Qaboos University, Al-Khoud, 123, Oman; Corresponding author.Nanotechnology Research Center, Sultan Qaboos University, Al-Khoud, 123, Oman; Department of Petroleum and Chemical Engineering, College of Engineering, Sultan Qaboos University, Al-Khoud, 123, OmanDepartment of Electrical and Computer Engineering, College of Engineering and Architecture, University of Nizwa, Birkat Al Mawz, OmanThe variability in the spatiotemporal distribution of power generation is a significant challenge for accurately predicting renewable energy production patterns. Furthermore, numerous forms of unforeseen data contamination degrade the precision of forecasts since superfluous data points adversely affect the regression model. In this context, a novel robust deep learning model, termed the Convolutional Neural Network-Bidirectional Long Short-Term Memory model with spatiotemporal attention mechanism (CNN-BiLSTM-STA), is developed in this study. The suggested model integrates the feature extraction expertise of CNNs with the sequence modeling proficiency of BiLSTM networks to capture spatial linkages and temporal interdependence adeptly. Moreover, the integrated spatiotemporal attention mechanism selectively focuses on significant spatial regions and time steps to enhance the prediction of spatiotemporal sequences of time-resolved grid data. The proposed architecture allows plant proprietors and system operators to obtain accurate predictions across extensive spatiotemporal patterns by eliminating the necessity for individual model fitting for each site/horizon or an additional data preprocessing phase before training. In addition, the Correntropy-based training criterion is employed to ensure the robustness of the recommended method against various types of data contamination, including data incompletion, Gaussian noises, outliers, and a mixed combination of disturbances. Furthermore, the Partial Reinforcement Optimization technique is applied to optimize the hyperparameters of the proposed model. The suggested framework incorporates numerous photovoltaic installations in Arizona and wind power installations in Texas to provide concurrent forecasts for multiple periods. The efficacy of the suggested forecasting model is evaluated by comparing it with three state-of-the-art methods. Numerical findings demonstrate that the proposed model surpasses other methods by successfully integrating spatial and temporal characteristics.http://www.sciencedirect.com/science/article/pii/S2590174525000510Renewable energySolar energyWind energySpatiotemporal forecastingBiLSTMPartial reinforcement optimization
spellingShingle Md. Shadman Abid
Razzaqul Ahshan
Mohammed Al-Abri
Rashid Al Abri
Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
Energy Conversion and Management: X
Renewable energy
Solar energy
Wind energy
Spatiotemporal forecasting
BiLSTM
Partial reinforcement optimization
title Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
title_full Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
title_fullStr Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
title_full_unstemmed Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
title_short Spatiotemporal Forecasting of Solar and Wind Energy Production: A Robust Deep Learning Model with Attention Framework
title_sort spatiotemporal forecasting of solar and wind energy production a robust deep learning model with attention framework
topic Renewable energy
Solar energy
Wind energy
Spatiotemporal forecasting
BiLSTM
Partial reinforcement optimization
url http://www.sciencedirect.com/science/article/pii/S2590174525000510
work_keys_str_mv AT mdshadmanabid spatiotemporalforecastingofsolarandwindenergyproductionarobustdeeplearningmodelwithattentionframework
AT razzaqulahshan spatiotemporalforecastingofsolarandwindenergyproductionarobustdeeplearningmodelwithattentionframework
AT mohammedalabri spatiotemporalforecastingofsolarandwindenergyproductionarobustdeeplearningmodelwithattentionframework
AT rashidalabri spatiotemporalforecastingofsolarandwindenergyproductionarobustdeeplearningmodelwithattentionframework