Hybrid deep learning CNN-LSTM model for forecasting direct normal irradiance: a study on solar potential in Ghardaia, Algeria

被引：0

作者：

Boumediene Ladjal ^{[1
]}

Mohamed Nadour ^{[2
]}

Mohcene Bechouat ^{[1
]}

Nadji Hadroug ^{[2
]}

Moussa Sedraoui ^{[3
]}

Abdelaziz Rabehi ^{[4
]}

Mawloud Guermoui ^{[4
]}

Takele Ferede Agajie ^{[5
]}

机构：

[1] Department of Automation and Electromechanics, Faculty of Science and Technology, University of Ghardaïa, Ghardaïa

[2] Applied Automation and Industrial Diagnostics Laboratory (LAADI), Faculty of Sciences and Technology, University of Djelfa, Djelfa

[3] Laboratory of Inverse Problems, Modeling, Information and Systems (PI:MIS), University 8 Mai 1945, Guelma

[4] Telecommunications and Smart Systems Laboratory, University of Djelfa, PO Box 3117, Djelfa

[5] Centre de Développement des Energies Renouvelables, Unité de Recherche Appliquée en Energies Renouvelables, URAER, CDER, Ghardaïa

[6] Department of Electrical and Computer Engineering, Faculty of Technology, Debre Markos University, Debre Markos

来源：

Scientific Reports | / 15卷 / 1期

关键词：

Artificial neural networks; Convolutional feed-forward back propagation; Convolutional neural network; Deep learning; Feed-forward back propagation; Long short-term memory; Solar radiance forecasting;

D O I：

10.1038/s41598-025-94239-z

中图分类号：

学科分类号：

摘要：

This paper provides an in-depth analysis and performance evaluation of four Solar Radiance (SR) prediction models. The prediction is ensured for a period ranging from a few hours to several days of the year. These models are derived from four machine learning methods, namely the Feed-forward Back Propagation (FFBP) method, Convolutional Feed-forward Back Propagation (CFBP) method, Support Vector Regression (SVR), and the hybrid deep learning (DL) method, which combines Convolutional Neural Networks and Long Short-Term Memory networks. This combination results in the CNN-LSTM model. Additionally, statistical indicators use Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Normalized Root Mean Squared Error (nRMSE). Each indicator compares the predicted output by each model above and the actual output, pre-recorded in the experimental trial. The experimental results consistently show the power of the CNN-LSTM model compared to the remaining models in terms of accuracy and reliability. This is due to its lower error rate and higher detection coefficient (R2 = 0.99925). © The Author(s) 2025.

引用

共 53 条

[1]

Hassan Q., Et al., The renewable energy role in the global energy transformations, Renew. Energy Focus, 48, (2024)

[2]

Sovacool B.K., Baum C.M., Low S., Climate protection or privilege? A whole systems justice milieu of twenty negative emissions and solar geoengineering technologies, Polit. Geogr, 97, (2022)

[3]

Qadir Z., Et al., Predicting the energy output of hybrid PV–wind renewable energy system using feature selection technique for smart grids, Energy Rep, 7, pp. 8465-8475, (2021)

[4]

Irfan M., Et al., Radiative forcing on climate change: assessing the effect of greenhouse gases on energy balance of Earth, Adv. Technol. Dev. Greenhouse Gases: Emission, Capture Convers, 2024, pp. 137-167, (2024)

[5]

Kumari P., Toshniwal D., Deep learning models for solar irradiance forecasting: a comprehensive review, J. Clean. Prod, 318, (2021)

[6]

Ahmed R., Et al., A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization, Renew. Sustain. Energy Rev, 124, (2020)

[7]

Zhou Y., Et al., A review on global solar radiance prediction with machine learning models in a comprehensive perspective, Energy Convers. Manage, 235, (2021)

[8]

Krishnan N., Et al., How solar radiance forecasting impacts the utilization of solar energy: a critical review, J. Clean. Prod, 388, (2023)

[9]

Guermoui M., Et al., An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques, Sci. Rep, 14, 1, (2024)

[10]

AlKandari M., Ahmad I., Solar power generation forecasting using ensemble approach based on deep learning and statistical methods, Appl. Comput. Inf, 20, 3-4, pp. 231-250, (2024)

← 1 2 3 4 5 6 →