Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU

Abstract Accurately predicting solar power is essential for ensuring electric grid reliability and integrating renewable energy sources. This paper presents a novel approach to probabilistic solar power forecasting by combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) int...

Full description

Saved in:
Bibliographic Details
Main Authors: Louiza Ait Mouloud, Aissa Kheldoun, Samira Oussidhoum, Hisham Alharbi, Saud Alotaibi, Thabet Alzahrani, Takele Ferede Agajie
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12797-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235466645143552
author Louiza Ait Mouloud
Aissa Kheldoun
Samira Oussidhoum
Hisham Alharbi
Saud Alotaibi
Thabet Alzahrani
Takele Ferede Agajie
author_facet Louiza Ait Mouloud
Aissa Kheldoun
Samira Oussidhoum
Hisham Alharbi
Saud Alotaibi
Thabet Alzahrani
Takele Ferede Agajie
author_sort Louiza Ait Mouloud
collection DOAJ
description Abstract Accurately predicting solar power is essential for ensuring electric grid reliability and integrating renewable energy sources. This paper presents a novel approach to probabilistic solar power forecasting by combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) into a hybrid Quantile-CNN-GRU model. The proposed model generates intra-day probabilistic quantile forecasts and is rigorously evaluated using datasets from geographically and climatically diverse regions and hemispheres: the Netherlands (temperate maritime climate), Alice Springs (arid desert climate), and Hebei (humid subtropical climate). These datasets cover varied temporal horizons (1-hour, 6-hour, 12-hour, and 24-hour predictions) and seasonal conditions (summer, fall, spring, and winter), highlighting the model’s adaptability to different scenarios. The performance of the proposed Quantile-CNN-GRU model is benchmarked against state-of-the-art deep learning models, including standalone quantile-based architectures such as Quantile-GRU and Quantile-Long Short Term Memory (LSTM). A comprehensive evaluation framework is applied, employing probabilistic tools like the Continuous Ranked Probability Score (CRPS) for assessing forecast reliability, sharpness, and reliability diagrams with consistency bars to evaluate the calibration of the predictions. Results demonstrate that the proposed Quantile-CNN-GRU model consistently outperforms its counterparts in terms of CRPS, across varying forecast horizons and seasonal conditions. To further enhance performance, a multivariate case study incorporating exogenous inputs, specifically Numerical Weather Prediction (NWP) data, is conducted. Through sensitivity analysis, the influence of these additional inputs on forecast horizons and seasonal variability is systematically explored. The study reveals that integrating NWP data significantly improves the model’s predictive skill, particularly for longer forecast horizons and during transitional seasons like spring and fall, when solar variability is higher.
format Article
id doaj-art-7cf1e6347f1447e8ab2ac4480c59a0da
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7cf1e6347f1447e8ab2ac4480c59a0da2025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-07-0115111910.1038/s41598-025-12797-8Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRULouiza Ait Mouloud0Aissa Kheldoun1Samira Oussidhoum2Hisham Alharbi3Saud Alotaibi4Thabet Alzahrani5Takele Ferede Agajie6Laboratory of Signals Systems, Institute of Electrical and Electronic Engineering, University M’hamed BougaraLaboratory of Signals Systems, Institute of Electrical and Electronic Engineering, University M’hamed BougaraLaboratoire de Technologies Avancées en Génie Électrique, Mouloud Mammeri UniversityDepartment of Electrical Engineering, College of Engineering, Taif UniversityElectrical Engineering Department, College of Engineering, Shaqra UniversityElectrical Engineering Department, College of Engineering, Shaqra UniversityDepartment of Electrical and Computer Engineering, Faculty of Technology, DebreMarkos UniversityAbstract Accurately predicting solar power is essential for ensuring electric grid reliability and integrating renewable energy sources. This paper presents a novel approach to probabilistic solar power forecasting by combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) into a hybrid Quantile-CNN-GRU model. The proposed model generates intra-day probabilistic quantile forecasts and is rigorously evaluated using datasets from geographically and climatically diverse regions and hemispheres: the Netherlands (temperate maritime climate), Alice Springs (arid desert climate), and Hebei (humid subtropical climate). These datasets cover varied temporal horizons (1-hour, 6-hour, 12-hour, and 24-hour predictions) and seasonal conditions (summer, fall, spring, and winter), highlighting the model’s adaptability to different scenarios. The performance of the proposed Quantile-CNN-GRU model is benchmarked against state-of-the-art deep learning models, including standalone quantile-based architectures such as Quantile-GRU and Quantile-Long Short Term Memory (LSTM). A comprehensive evaluation framework is applied, employing probabilistic tools like the Continuous Ranked Probability Score (CRPS) for assessing forecast reliability, sharpness, and reliability diagrams with consistency bars to evaluate the calibration of the predictions. Results demonstrate that the proposed Quantile-CNN-GRU model consistently outperforms its counterparts in terms of CRPS, across varying forecast horizons and seasonal conditions. To further enhance performance, a multivariate case study incorporating exogenous inputs, specifically Numerical Weather Prediction (NWP) data, is conducted. Through sensitivity analysis, the influence of these additional inputs on forecast horizons and seasonal variability is systematically explored. The study reveals that integrating NWP data significantly improves the model’s predictive skill, particularly for longer forecast horizons and during transitional seasons like spring and fall, when solar variability is higher.https://doi.org/10.1038/s41598-025-12797-8Solar powerSeasonal forecastingQuantile probabilistic forecastingDeep learningContinuous ranked probability score (CRPS)Reliability diagram
spellingShingle Louiza Ait Mouloud
Aissa Kheldoun
Samira Oussidhoum
Hisham Alharbi
Saud Alotaibi
Thabet Alzahrani
Takele Ferede Agajie
Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
Scientific Reports
Solar power
Seasonal forecasting
Quantile probabilistic forecasting
Deep learning
Continuous ranked probability score (CRPS)
Reliability diagram
title Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
title_full Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
title_fullStr Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
title_full_unstemmed Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
title_short Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
title_sort seasonal quantile forecasting of solar photovoltaic power using q cnn gru
topic Solar power
Seasonal forecasting
Quantile probabilistic forecasting
Deep learning
Continuous ranked probability score (CRPS)
Reliability diagram
url https://doi.org/10.1038/s41598-025-12797-8
work_keys_str_mv AT louizaaitmouloud seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT aissakheldoun seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT samiraoussidhoum seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT hishamalharbi seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT saudalotaibi seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT thabetalzahrani seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru
AT takeleferedeagajie seasonalquantileforecastingofsolarphotovoltaicpowerusingqcnngru