PV power forecasting based on data-driven models: a review
Accurate PV power forecasting techniques are a prerequisite for the optimal management of the grid and its stability. This paper presents a review of the recent developments in the field of PV power forecasting, mainly focusing on the literature which uses ML techniques. The ML techniques (sub-branc...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-11-01
|
| Series: | International Journal of Sustainable Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/19397038.2021.1986590 |
| _version_ | 1797678324345995264 |
|---|---|
| author | Priya Gupta Rhythm Singh |
| author_facet | Priya Gupta Rhythm Singh |
| author_sort | Priya Gupta |
| collection | DOAJ |
| description | Accurate PV power forecasting techniques are a prerequisite for the optimal management of the grid and its stability. This paper presents a review of the recent developments in the field of PV power forecasting, mainly focusing on the literature which uses ML techniques. The ML techniques (sub-branch of artificial intelligence) are extensively used due to their ability to solve nonlinear and complex data structures. PV power forecasting can either be direct, or indirect, which involves solar irradiance forecast model, plane of array irradiance estimation model, and PV performance model. This paper presents a review of both of these pathways of PV power forecasting based on the proposed methodology, forecast horizons and the considered input parameters. In case of unavailability of historical PV power for a new PV plant and in case of failure of real-time data acquisition, indirect PV power forecasting can be a viable alternative. Although the performance ranking of various ML models is complicated and no model is universal, recent studies suggest that methodologies like deep neural networks and ensemble or hybrid models outperform conventional methods for short-term PV forecasting. Recent articles also present the various intelligent optimisation and data-preparation techniques to improve performance accuracy. |
| first_indexed | 2024-03-11T22:58:04Z |
| format | Article |
| id | doaj.art-f06387f12953409686af5c1ab2c9e38a |
| institution | Directory Open Access Journal |
| issn | 1939-7038 1939-7046 |
| language | English |
| last_indexed | 2024-03-11T22:58:04Z |
| publishDate | 2021-11-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Sustainable Engineering |
| spelling | doaj.art-f06387f12953409686af5c1ab2c9e38a2023-09-21T15:17:05ZengTaylor & Francis GroupInternational Journal of Sustainable Engineering1939-70381939-70462021-11-011461733175510.1080/19397038.2021.19865901986590PV power forecasting based on data-driven models: a reviewPriya Gupta0Rhythm Singh1Indian Institute of Technology RoorkeeIndian Institute of Technology RoorkeeAccurate PV power forecasting techniques are a prerequisite for the optimal management of the grid and its stability. This paper presents a review of the recent developments in the field of PV power forecasting, mainly focusing on the literature which uses ML techniques. The ML techniques (sub-branch of artificial intelligence) are extensively used due to their ability to solve nonlinear and complex data structures. PV power forecasting can either be direct, or indirect, which involves solar irradiance forecast model, plane of array irradiance estimation model, and PV performance model. This paper presents a review of both of these pathways of PV power forecasting based on the proposed methodology, forecast horizons and the considered input parameters. In case of unavailability of historical PV power for a new PV plant and in case of failure of real-time data acquisition, indirect PV power forecasting can be a viable alternative. Although the performance ranking of various ML models is complicated and no model is universal, recent studies suggest that methodologies like deep neural networks and ensemble or hybrid models outperform conventional methods for short-term PV forecasting. Recent articles also present the various intelligent optimisation and data-preparation techniques to improve performance accuracy.http://dx.doi.org/10.1080/19397038.2021.1986590pv power forecastingforecast horizondata-driven modelsmachine learningdeep learningensemble methodssolar radiation forecastingpoa irradiancepv performance models |
| spellingShingle | Priya Gupta Rhythm Singh PV power forecasting based on data-driven models: a review International Journal of Sustainable Engineering pv power forecasting forecast horizon data-driven models machine learning deep learning ensemble methods solar radiation forecasting poa irradiance pv performance models |
| title | PV power forecasting based on data-driven models: a review |
| title_full | PV power forecasting based on data-driven models: a review |
| title_fullStr | PV power forecasting based on data-driven models: a review |
| title_full_unstemmed | PV power forecasting based on data-driven models: a review |
| title_short | PV power forecasting based on data-driven models: a review |
| title_sort | pv power forecasting based on data driven models a review |
| topic | pv power forecasting forecast horizon data-driven models machine learning deep learning ensemble methods solar radiation forecasting poa irradiance pv performance models |
| url | http://dx.doi.org/10.1080/19397038.2021.1986590 |
| work_keys_str_mv | AT priyagupta pvpowerforecastingbasedondatadrivenmodelsareview AT rhythmsingh pvpowerforecastingbasedondatadrivenmodelsareview |