Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning
This article highlights the industry experience of the development and practical implementation of a short-term photovoltaic forecasting system based on machine learning methods for a real industry-scale photovoltaic power plant implemented in a Russian power system using remote data acquisition. On...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/20/3420 |
| _version_ | 1797550618442727424 |
|---|---|
| author | Alexandra I. Khalyasmaa Stanislav A. Eroshenko Valeriy A. Tashchilin Hariprakash Ramachandran Teja Piepur Chakravarthi Denis N. Butusov |
| author_facet | Alexandra I. Khalyasmaa Stanislav A. Eroshenko Valeriy A. Tashchilin Hariprakash Ramachandran Teja Piepur Chakravarthi Denis N. Butusov |
| author_sort | Alexandra I. Khalyasmaa |
| collection | DOAJ |
| description | This article highlights the industry experience of the development and practical implementation of a short-term photovoltaic forecasting system based on machine learning methods for a real industry-scale photovoltaic power plant implemented in a Russian power system using remote data acquisition. One of the goals of the study is to improve photovoltaic power plants generation forecasting accuracy based on open-source meteorological data, which is provided in regular weather forecasts. In order to improve the robustness of the system in terms of the forecasting accuracy, we apply newly derived feature introduction, a factor obtained as a result of feature engineering procedure, characterizing the relationship between photovoltaic power plant energy production and solar irradiation on a horizontal surface, thus taking into account the impacts of atmospheric and electrical nature. The article scrutinizes the application of different machine learning algorithms, including Random Forest regressor, Gradient Boosting Regressor, Linear Regression and Decision Trees regression, to the remotely obtained data. As a result of the application of the aforementioned approaches together with hyperparameters, tuning and pipelining of the algorithms, the optimal structure, parameters and the application sphere of different regressors were identified for various testing samples. The mathematical model developed within the framework of the study gave us the opportunity to provide robust photovoltaic energy forecasting results with mean accuracy over 92% for mostly-sunny sample days and over 83% for mostly cloudy days with different types of precipitation. |
| first_indexed | 2024-03-10T15:31:52Z |
| format | Article |
| id | doaj.art-caef643984eb420c95559e18984044c7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:31:52Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-caef643984eb420c95559e18984044c72023-11-20T17:34:44ZengMDPI AGRemote Sensing2072-42922020-10-011220342010.3390/rs12203420Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine LearningAlexandra I. Khalyasmaa0Stanislav A. Eroshenko1Valeriy A. Tashchilin2Hariprakash Ramachandran3Teja Piepur Chakravarthi4Denis N. Butusov5Ural Power Engineering Institute, Ural Federal University named after the first President of Russia B.N. Yeltsin, 620002 Ekaterinburg, RussiaUral Power Engineering Institute, Ural Federal University named after the first President of Russia B.N. Yeltsin, 620002 Ekaterinburg, RussiaUral Power Engineering Institute, Ural Federal University named after the first President of Russia B.N. Yeltsin, 620002 Ekaterinburg, RussiaDepartment of Electrical and Electronics Engineering, Bharath Institute of Higher Education and Research, Chennai 600073, IndiaDepartment of Computer Science and Engineering, Bharath Institute of Higher Education and Research, Chennai 600073, IndiaYouth Research Institute, Saint Petersburg Electrotechnical University “LETI”, 197376 Saint Petersburg, RussiaThis article highlights the industry experience of the development and practical implementation of a short-term photovoltaic forecasting system based on machine learning methods for a real industry-scale photovoltaic power plant implemented in a Russian power system using remote data acquisition. One of the goals of the study is to improve photovoltaic power plants generation forecasting accuracy based on open-source meteorological data, which is provided in regular weather forecasts. In order to improve the robustness of the system in terms of the forecasting accuracy, we apply newly derived feature introduction, a factor obtained as a result of feature engineering procedure, characterizing the relationship between photovoltaic power plant energy production and solar irradiation on a horizontal surface, thus taking into account the impacts of atmospheric and electrical nature. The article scrutinizes the application of different machine learning algorithms, including Random Forest regressor, Gradient Boosting Regressor, Linear Regression and Decision Trees regression, to the remotely obtained data. As a result of the application of the aforementioned approaches together with hyperparameters, tuning and pipelining of the algorithms, the optimal structure, parameters and the application sphere of different regressors were identified for various testing samples. The mathematical model developed within the framework of the study gave us the opportunity to provide robust photovoltaic energy forecasting results with mean accuracy over 92% for mostly-sunny sample days and over 83% for mostly cloudy days with different types of precipitation.https://www.mdpi.com/2072-4292/12/20/3420feature engineeringforecastinggraphical user interface softwaremachine learningphotovoltaic power plant |
| spellingShingle | Alexandra I. Khalyasmaa Stanislav A. Eroshenko Valeriy A. Tashchilin Hariprakash Ramachandran Teja Piepur Chakravarthi Denis N. Butusov Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning Remote Sensing feature engineering forecasting graphical user interface software machine learning photovoltaic power plant |
| title | Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning |
| title_full | Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning |
| title_fullStr | Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning |
| title_full_unstemmed | Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning |
| title_short | Industry Experience of Developing Day-Ahead Photovoltaic Plant Forecasting System Based on Machine Learning |
| title_sort | industry experience of developing day ahead photovoltaic plant forecasting system based on machine learning |
| topic | feature engineering forecasting graphical user interface software machine learning photovoltaic power plant |
| url | https://www.mdpi.com/2072-4292/12/20/3420 |
| work_keys_str_mv | AT alexandraikhalyasmaa industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning AT stanislavaeroshenko industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning AT valeriyatashchilin industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning AT hariprakashramachandran industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning AT tejapiepurchakravarthi industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning AT denisnbutusov industryexperienceofdevelopingdayaheadphotovoltaicplantforecastingsystembasedonmachinelearning |