An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information
In the context of global warming, renewable energy sources, particularly wind and solar power, have garnered increasing attention in recent decades. Accurate forecasting of the energy output in microgrids (MGs) is essential for optimizing energy management, reducing maintenance costs, and prolonging...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/24/6361 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850240889303072768 |
|---|---|
| author | Mohamed Mroueh Moustapha Doumiati Clovis Francis Mohamed Machmoum |
| author_facet | Mohamed Mroueh Moustapha Doumiati Clovis Francis Mohamed Machmoum |
| author_sort | Mohamed Mroueh |
| collection | DOAJ |
| description | In the context of global warming, renewable energy sources, particularly wind and solar power, have garnered increasing attention in recent decades. Accurate forecasting of the energy output in microgrids (MGs) is essential for optimizing energy management, reducing maintenance costs, and prolonging the lifespan of energy storage systems. This study proposes an innovative approach to solar irradiance forecasting based on the theory of belief functions, introducing a novel and flexible evidential method for short-to-medium-term predictions. The proposed machine learning model is designed to effectively handle missing data and make optimal use of available information. By integrating multiple predictive models, each focusing on different meteorological factors, the approach enhances forecasting accuracy. The Yager combination method and pignistic transformation are utilized to aggregate the individual models. Applied to a publicly available dataset, the method achieved promising results, with an average root mean square error (RMS) of 27.83 W/m<sup>2</sup> calculated from eight distinct forecast days. This performance surpasses the best reported results of 30.21 W/m<sup>2</sup> from recent comparable studies for one-day-ahead solar irradiance forecasting. Comparisons with deep learning-based methods, such as long short-term memory (LSTM) networks and recurrent neural networks (RNNs), demonstrate that the proposed approach is competitive with state-of-the-art techniques, delivering reliable predictions with significantly less training data. The full potential and limitations of the proposed approach are also discussed. |
| format | Article |
| id | doaj-art-1ff3fab891e640bc8f7115fd6855ed51 |
| institution | OA Journals |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-1ff3fab891e640bc8f7115fd6855ed512025-08-20T02:00:45ZengMDPI AGEnergies1996-10732024-12-011724636110.3390/en17246361An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of InformationMohamed Mroueh0Moustapha Doumiati1Clovis Francis2Mohamed Machmoum3Triskell Consulting, 32 Rue Arago, 92800 Puteaux, FranceIREENA Lab UR 4642, Electrical and Electronics Department, ESEO, 10 Bd Jeanneteau, 49100 Angers, FranceArts et Métiers Paris Tech, Châlons en Champagne, Department of Design, Industrialization, Risk, and Decision (CIRD), 51000 Châlons en Champagne, FranceIREENA Lab UR 4642, Nantes University, 37 Bd de l’université, 44602 Saint Nazaire, FranceIn the context of global warming, renewable energy sources, particularly wind and solar power, have garnered increasing attention in recent decades. Accurate forecasting of the energy output in microgrids (MGs) is essential for optimizing energy management, reducing maintenance costs, and prolonging the lifespan of energy storage systems. This study proposes an innovative approach to solar irradiance forecasting based on the theory of belief functions, introducing a novel and flexible evidential method for short-to-medium-term predictions. The proposed machine learning model is designed to effectively handle missing data and make optimal use of available information. By integrating multiple predictive models, each focusing on different meteorological factors, the approach enhances forecasting accuracy. The Yager combination method and pignistic transformation are utilized to aggregate the individual models. Applied to a publicly available dataset, the method achieved promising results, with an average root mean square error (RMS) of 27.83 W/m<sup>2</sup> calculated from eight distinct forecast days. This performance surpasses the best reported results of 30.21 W/m<sup>2</sup> from recent comparable studies for one-day-ahead solar irradiance forecasting. Comparisons with deep learning-based methods, such as long short-term memory (LSTM) networks and recurrent neural networks (RNNs), demonstrate that the proposed approach is competitive with state-of-the-art techniques, delivering reliable predictions with significantly less training data. The full potential and limitations of the proposed approach are also discussed.https://www.mdpi.com/1996-1073/17/24/6361machine learningsolar energybelief functions theoryinformation fusion |
| spellingShingle | Mohamed Mroueh Moustapha Doumiati Clovis Francis Mohamed Machmoum An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information Energies machine learning solar energy belief functions theory information fusion |
| title | An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information |
| title_full | An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information |
| title_fullStr | An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information |
| title_full_unstemmed | An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information |
| title_short | An Evidential Solar Irradiance Forecasting Method Using Multiple Sources of Information |
| title_sort | evidential solar irradiance forecasting method using multiple sources of information |
| topic | machine learning solar energy belief functions theory information fusion |
| url | https://www.mdpi.com/1996-1073/17/24/6361 |
| work_keys_str_mv | AT mohamedmroueh anevidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT moustaphadoumiati anevidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT clovisfrancis anevidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT mohamedmachmoum anevidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT mohamedmroueh evidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT moustaphadoumiati evidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT clovisfrancis evidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation AT mohamedmachmoum evidentialsolarirradianceforecastingmethodusingmultiplesourcesofinformation |