A new climatology reference model to benchmark probabilistic solar forecasts.
Saved in:
| Title: | A new climatology reference model to benchmark probabilistic solar forecasts. |
|---|---|
| Authors: | Le Gal La Salle, Josselin1 (AUTHOR) josselin.le-gal-la-salle@univ-reunion.fr, David, Mathieu1 (AUTHOR), Lauret, Philippe1 (AUTHOR) |
| Source: | Solar Energy. Jul2021, Vol. 223, p398-414. 17p. |
| Subjects: | Climatology, Data binning, Forecasting, Distribution (Probability theory), Scientific community, Best practices |
| Abstract: | • A new reference model for probabilistic solar forecasts called "CSD-CLIM" is introduced. • There is no need to form probability distributions to compute its CRPS. • A baseline for climatology benchmark models is proposed and used to compare models. • CSD-CLIM is easy-to-implement and meets all prerequisite properties of a good benchmark model. • CSD-CLIM achieves the best trade-off between reliability and resolution. • It can be a viable alternative to existing reference models. Probabilistic solar forecasting is becoming a major topic in the solar research community as it provides more information about the uncertainty of the forecast compared to deterministic forecasting. However, to facilitate the adoption of probabilistic forecasts within solar forecasting communities (industry and academic), the definition and the use of standardized best practices are a prerequisite. Among others, there is a need for benchmark models that are able to properly assess the performance of new probabilistic forecasting methods. In this work, we propose a new climatology benchmark model called "CSD-CLIM" (for Clear-Sky Dependent Climatology). This new reference model is evaluated against two other climatology benchmark models namely the naive climatology and a well-referenced model in the literature, the CH-PeEn (for Complete History Persistence Ensemble). The verification of compliance with a set of properties that a climatology benchmark model must follow demonstrates that the new CSD-CLIM model outperforms the naive climatology and that it can be a viable alternative to the CH-PeEn model. It is shown that the better performance of CSD-CLIM is due to a specific binning of the historical irradiance data based on the clear-sky irradiance values. [ABSTRACT FROM AUTHOR] |
| Copyright of Solar Energy is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 150819537 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A new climatology reference model to benchmark probabilistic solar forecasts. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Le+Gal+La+Salle%2C+Josselin%22">Le Gal La Salle, Josselin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> josselin.le-gal-la-salle@univ-reunion.fr</i><br /><searchLink fieldCode="AR" term="%22David%2C+Mathieu%22">David, Mathieu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lauret%2C+Philippe%22">Lauret, Philippe</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Solar+Energy%22">Solar Energy</searchLink>. Jul2021, Vol. 223, p398-414. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Climatology%22">Climatology</searchLink><br /><searchLink fieldCode="DE" term="%22Data+binning%22">Data binning</searchLink><br /><searchLink fieldCode="DE" term="%22Forecasting%22">Forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Distribution+%28Probability+theory%29%22">Distribution (Probability theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Scientific+community%22">Scientific community</searchLink><br /><searchLink fieldCode="DE" term="%22Best+practices%22">Best practices</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: • A new reference model for probabilistic solar forecasts called "CSD-CLIM" is introduced. • There is no need to form probability distributions to compute its CRPS. • A baseline for climatology benchmark models is proposed and used to compare models. • CSD-CLIM is easy-to-implement and meets all prerequisite properties of a good benchmark model. • CSD-CLIM achieves the best trade-off between reliability and resolution. • It can be a viable alternative to existing reference models. Probabilistic solar forecasting is becoming a major topic in the solar research community as it provides more information about the uncertainty of the forecast compared to deterministic forecasting. However, to facilitate the adoption of probabilistic forecasts within solar forecasting communities (industry and academic), the definition and the use of standardized best practices are a prerequisite. Among others, there is a need for benchmark models that are able to properly assess the performance of new probabilistic forecasting methods. In this work, we propose a new climatology benchmark model called "CSD-CLIM" (for Clear-Sky Dependent Climatology). This new reference model is evaluated against two other climatology benchmark models namely the naive climatology and a well-referenced model in the literature, the CH-PeEn (for Complete History Persistence Ensemble). The verification of compliance with a set of properties that a climatology benchmark model must follow demonstrates that the new CSD-CLIM model outperforms the naive climatology and that it can be a viable alternative to the CH-PeEn model. It is shown that the better performance of CSD-CLIM is due to a specific binning of the historical irradiance data based on the clear-sky irradiance values. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Solar Energy is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=150819537 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.solener.2021.05.037 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 398 Subjects: – SubjectFull: Climatology Type: general – SubjectFull: Data binning Type: general – SubjectFull: Forecasting Type: general – SubjectFull: Distribution (Probability theory) Type: general – SubjectFull: Scientific community Type: general – SubjectFull: Best practices Type: general Titles: – TitleFull: A new climatology reference model to benchmark probabilistic solar forecasts. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Le Gal La Salle, Josselin – PersonEntity: Name: NameFull: David, Mathieu – PersonEntity: Name: NameFull: Lauret, Philippe IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 07 Text: Jul2021 Type: published Y: 2021 Identifiers: – Type: issn-print Value: 0038092X Numbering: – Type: volume Value: 223 Titles: – TitleFull: Solar Energy Type: main |
| ResultId | 1 |
