Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study
In the present paper, global horizontal irradiance (GHI) is modelled and forecasted at time horizons ranging from 30 <inline-formula><math display="inline"><semantics><mi>min</mi></semantics></math></inline-formula> to 48 <inline-formula&g...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/16/4184 |
| _version_ | 1827709963110187008 |
|---|---|
| author | Hanany Tolba Nouha Dkhili Julien Nou Julien Eynard Stéphane Thil Stéphane Grieu |
| author_facet | Hanany Tolba Nouha Dkhili Julien Nou Julien Eynard Stéphane Thil Stéphane Grieu |
| author_sort | Hanany Tolba |
| collection | DOAJ |
| description | In the present paper, global horizontal irradiance (GHI) is modelled and forecasted at time horizons ranging from 30 <inline-formula><math display="inline"><semantics><mi>min</mi></semantics></math></inline-formula> to 48 <inline-formula><math display="inline"><semantics><mi mathvariant="normal">h</mi></semantics></math></inline-formula>, thus covering intrahour, intraday and intraweek cases, using online Gaussian process regression (OGPR) and online sparse Gaussian process regression (OSGPR). The covariance function, also known as the kernel, is a key element that deeply influences forecasting accuracy. As a consequence, a comparative study of OGPR and OSGPR models based on simple kernels or combined kernels defined as sums or products of simple kernels has been carried out. The classic persistence model is included in the comparative study. Thanks to two datasets composed of GHI measurements (45 days), we have been able to show that OGPR models based on quasiperiodic kernels outperform the persistence model as well as OGPR models based on simple kernels, including the squared exponential kernel, which is widely used for GHI forecasting. Indeed, although all OGPR models give good results when the forecast horizon is short-term, when the horizon increases, the superiority of quasiperiodic kernels becomes apparent. A simple online sparse GPR (OSGPR) approach has also been assessed. This approach gives less precise results than standard GPR, but the training computation time is decreased to a great extent. Even though the lack of data hinders the training process, the results still show the superiority of GPR models based on quasiperiodic kernels for GHI forecasting. |
| first_indexed | 2024-03-10T17:31:32Z |
| format | Article |
| id | doaj.art-571a24636a2e48abb039f2b18e8a434c |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T17:31:32Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-571a24636a2e48abb039f2b18e8a434c2023-11-20T10:00:48ZengMDPI AGEnergies1996-10732020-08-011316418410.3390/en13164184Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel StudyHanany Tolba0Nouha Dkhili1Julien Nou2Julien Eynard3Stéphane Thil4Stéphane Grieu5PROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FrancePROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FrancePROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FrancePROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FrancePROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FrancePROMES-CNRS Laboratory (UPR 8521), Rambla de la Thermodynamique, Tecnosud, 66100 Perpignan, FranceIn the present paper, global horizontal irradiance (GHI) is modelled and forecasted at time horizons ranging from 30 <inline-formula><math display="inline"><semantics><mi>min</mi></semantics></math></inline-formula> to 48 <inline-formula><math display="inline"><semantics><mi mathvariant="normal">h</mi></semantics></math></inline-formula>, thus covering intrahour, intraday and intraweek cases, using online Gaussian process regression (OGPR) and online sparse Gaussian process regression (OSGPR). The covariance function, also known as the kernel, is a key element that deeply influences forecasting accuracy. As a consequence, a comparative study of OGPR and OSGPR models based on simple kernels or combined kernels defined as sums or products of simple kernels has been carried out. The classic persistence model is included in the comparative study. Thanks to two datasets composed of GHI measurements (45 days), we have been able to show that OGPR models based on quasiperiodic kernels outperform the persistence model as well as OGPR models based on simple kernels, including the squared exponential kernel, which is widely used for GHI forecasting. Indeed, although all OGPR models give good results when the forecast horizon is short-term, when the horizon increases, the superiority of quasiperiodic kernels becomes apparent. A simple online sparse GPR (OSGPR) approach has also been assessed. This approach gives less precise results than standard GPR, but the training computation time is decreased to a great extent. Even though the lack of data hinders the training process, the results still show the superiority of GPR models based on quasiperiodic kernels for GHI forecasting.https://www.mdpi.com/1996-1073/13/16/4184solar resourceglobal horizontal irradiancetime series forecastingmachine learningonline Gaussian process regressiononline sparse Gaussian process regression |
| spellingShingle | Hanany Tolba Nouha Dkhili Julien Nou Julien Eynard Stéphane Thil Stéphane Grieu Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study Energies solar resource global horizontal irradiance time series forecasting machine learning online Gaussian process regression online sparse Gaussian process regression |
| title | Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study |
| title_full | Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study |
| title_fullStr | Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study |
| title_full_unstemmed | Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study |
| title_short | Multi-Horizon Forecasting of Global Horizontal Irradiance Using Online Gaussian Process Regression: A Kernel Study |
| title_sort | multi horizon forecasting of global horizontal irradiance using online gaussian process regression a kernel study |
| topic | solar resource global horizontal irradiance time series forecasting machine learning online Gaussian process regression online sparse Gaussian process regression |
| url | https://www.mdpi.com/1996-1073/13/16/4184 |
| work_keys_str_mv | AT hananytolba multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy AT nouhadkhili multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy AT juliennou multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy AT julieneynard multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy AT stephanethil multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy AT stephanegrieu multihorizonforecastingofglobalhorizontalirradianceusingonlinegaussianprocessregressionakernelstudy |