Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression
Probabilistic solar power forecasting has been critical in Southern Africa because of major shortages of power due to climatic changes and other factors over the past decade. This paper discusses Gaussian process regression (GPR) coupled with core vector regression for short-term hourly global horiz...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI
2022
|
| Subjects: | |
| Online Access: | https:// doi.org/10.3390/a14060177 http://hdl.handle.net/11408/4701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1779905362917326848 |
|---|---|
| author | Chandiwana, Edina Sigauke, Caston Bere, Alphonce |
| author_facet | Chandiwana, Edina Sigauke, Caston Bere, Alphonce |
| author_sort | Chandiwana, Edina |
| collection | DSpace |
| description | Probabilistic solar power forecasting has been critical in Southern Africa because of major shortages of power due to climatic changes and other factors over the past decade. This paper discusses Gaussian process regression (GPR) coupled with core vector regression for short-term hourly global horizontal irradiance (GHI) forecasting. GPR is a powerful Bayesian non-parametric regression method that works well for small data sets and quantifies the uncertainty in the predictions.
The choice of a kernel that characterises the covariance function is a crucial issue in Gaussian process regression. In this study, we adopt the minimum enclosing ball (MEB) technique. The MEB improves the forecasting power of GPR because the smaller the ball is, the shorter the training time, hence performance is robust. Forecasting of real-time data was done on two South African radiometric
stations, Stellenbosch University (SUN) in a coastal area of the Western Cape Province, and the University of Venda (UNV) station in the Limpopo Province. Variables were selected using the least absolute shrinkage and selection operator via hierarchical interactions. The Bayesian approach using informative priors was used for parameter estimation. Based on the root mean square error, mean absolute error and percentage bias the results showed that the GPR model gives the most accurate predictions compared to those from gradient boosting and support vector regression models, making this study a useful tool for decision-makers and system operators in power utility companies. The main contribution of this paper is in the use of a GPR model coupled with the core vector methodology which is used in forecasting GHI using South African data. This is the first application of GPR coupled with core vector regression in which the minimum enclosing ball is applied on GHI data, to the best of our knowledge. |
| format | Article |
| id | ir-11408-4701 |
| institution | My University |
| language | English |
| publishDate | 2022 |
| publisher | MDPI |
| record_format | dspace |
| spelling | ir-11408-47012022-06-27T13:49:07Z Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression Chandiwana, Edina Sigauke, Caston Bere, Alphonce Core vector regression Gaussian process Lasso Minimum enclosed ball Solar power Probabilistic solar power forecasting has been critical in Southern Africa because of major shortages of power due to climatic changes and other factors over the past decade. This paper discusses Gaussian process regression (GPR) coupled with core vector regression for short-term hourly global horizontal irradiance (GHI) forecasting. GPR is a powerful Bayesian non-parametric regression method that works well for small data sets and quantifies the uncertainty in the predictions. The choice of a kernel that characterises the covariance function is a crucial issue in Gaussian process regression. In this study, we adopt the minimum enclosing ball (MEB) technique. The MEB improves the forecasting power of GPR because the smaller the ball is, the shorter the training time, hence performance is robust. Forecasting of real-time data was done on two South African radiometric stations, Stellenbosch University (SUN) in a coastal area of the Western Cape Province, and the University of Venda (UNV) station in the Limpopo Province. Variables were selected using the least absolute shrinkage and selection operator via hierarchical interactions. The Bayesian approach using informative priors was used for parameter estimation. Based on the root mean square error, mean absolute error and percentage bias the results showed that the GPR model gives the most accurate predictions compared to those from gradient boosting and support vector regression models, making this study a useful tool for decision-makers and system operators in power utility companies. The main contribution of this paper is in the use of a GPR model coupled with the core vector methodology which is used in forecasting GHI using South African data. This is the first application of GPR coupled with core vector regression in which the minimum enclosing ball is applied on GHI data, to the best of our knowledge. 2022-03-16T12:12:15Z 2022-03-16T12:12:15Z 2021 Article 1999-4893 https:// doi.org/10.3390/a14060177 http://hdl.handle.net/11408/4701 en Algorithms;Vol. 14; No. 6 open MDPI |
| spellingShingle | Core vector regression Gaussian process Lasso Minimum enclosed ball Solar power Chandiwana, Edina Sigauke, Caston Bere, Alphonce Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title | Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title_full | Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title_fullStr | Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title_full_unstemmed | Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title_short | Twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| title_sort | twenty-four-hour ahead probabilistic global horizontal irradiance forecasting using gaussian process regression |
| topic | Core vector regression Gaussian process Lasso Minimum enclosed ball Solar power |
| url | https:// doi.org/10.3390/a14060177 http://hdl.handle.net/11408/4701 |
| work_keys_str_mv | AT chandiwanaedina twentyfourhouraheadprobabilisticglobalhorizontalirradianceforecastingusinggaussianprocessregression AT sigaukecaston twentyfourhouraheadprobabilisticglobalhorizontalirradianceforecastingusinggaussianprocessregression AT berealphonce twentyfourhouraheadprobabilisticglobalhorizontalirradianceforecastingusinggaussianprocessregression |