Adama II wind farm long-term power generation forecasting based on machine learning models
The present article develops time series machine learning models to forecast the Adama II wind farm's long-term power production using SCADA data. The study applied data from the previous six years (2016 to 2021) with five years of data for training the model and the remaining one year for test...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Scientific African |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468227623002879 |
| _version_ | 1797676257100431360 |
|---|---|
| author | Solomon Terefe Ayele Mesfin Belayneh Ageze Migbar Assefa Zeleke Temesgen Abriham Miliket |
| author_facet | Solomon Terefe Ayele Mesfin Belayneh Ageze Migbar Assefa Zeleke Temesgen Abriham Miliket |
| author_sort | Solomon Terefe Ayele |
| collection | DOAJ |
| description | The present article develops time series machine learning models to forecast the Adama II wind farm's long-term power production using SCADA data. The study applied data from the previous six years (2016 to 2021) with five years of data for training the model and the remaining one year for testing and validation. The study compares six supervised learning algorithms: Elastic net regression, Random forest regression, SARIMA, XGBoost, Prophet, and combined Prophet and XGBoost model. The projections for the 1-hour, 1-week, and 12-month forecasting ranges are compared for each forecasting model. The findings demonstrate that SARIMAX models outperform other models for forecasting one hour and one week, with a result of a 90% of R2 score and a 24% mean absolute percentage error (MAPE). However, XGBoost (with Fourier terms for seasonality) provides the foremost long-term forecasting result which is 7.33% MAPE for yearly prediction. Moreover, a combined Prophet and XGBoost for year-ahead wind power predictions has yield superior performance when compared to using each model individually which is 6.9% MAPE. Hence, for wind farms such as Adama II's long-term power forecasting, a combined prophet and XGBoost model fits well and provides accurate power generation insight. |
| first_indexed | 2024-03-11T22:26:22Z |
| format | Article |
| id | doaj.art-f11c0c05fff345978eca3c9d37bddeec |
| institution | Directory Open Access Journal |
| issn | 2468-2276 |
| language | English |
| last_indexed | 2024-03-11T22:26:22Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Scientific African |
| spelling | doaj.art-f11c0c05fff345978eca3c9d37bddeec2023-09-24T05:16:15ZengElsevierScientific African2468-22762023-09-0121e01831Adama II wind farm long-term power generation forecasting based on machine learning modelsSolomon Terefe Ayele0Mesfin Belayneh Ageze1Migbar Assefa Zeleke2Temesgen Abriham Miliket3Center for Renewable Energy, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa, Ethiopia; Ethiopia Electric Power, Addis Ababa, EthiopiaCenter for Renewable Energy, Addis Ababa Institute of Technology, Addis Ababa University, Addis Ababa, Ethiopia; Corresponding author.Department of Mechanical Engineering, Institute of Technology, Hawassa University, Ethiopia; Department of Mechanical Engineering, University of Botswana, Gaborone 0061, BotswanaBahir Dar Energy Center, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar, EthiopiaThe present article develops time series machine learning models to forecast the Adama II wind farm's long-term power production using SCADA data. The study applied data from the previous six years (2016 to 2021) with five years of data for training the model and the remaining one year for testing and validation. The study compares six supervised learning algorithms: Elastic net regression, Random forest regression, SARIMA, XGBoost, Prophet, and combined Prophet and XGBoost model. The projections for the 1-hour, 1-week, and 12-month forecasting ranges are compared for each forecasting model. The findings demonstrate that SARIMAX models outperform other models for forecasting one hour and one week, with a result of a 90% of R2 score and a 24% mean absolute percentage error (MAPE). However, XGBoost (with Fourier terms for seasonality) provides the foremost long-term forecasting result which is 7.33% MAPE for yearly prediction. Moreover, a combined Prophet and XGBoost for year-ahead wind power predictions has yield superior performance when compared to using each model individually which is 6.9% MAPE. Hence, for wind farms such as Adama II's long-term power forecasting, a combined prophet and XGBoost model fits well and provides accurate power generation insight.http://www.sciencedirect.com/science/article/pii/S2468227623002879Adama II Wind FarmWind farmLong-term power forecastingMachine learningXGBoostSARIMAX |
| spellingShingle | Solomon Terefe Ayele Mesfin Belayneh Ageze Migbar Assefa Zeleke Temesgen Abriham Miliket Adama II wind farm long-term power generation forecasting based on machine learning models Scientific African Adama II Wind Farm Wind farm Long-term power forecasting Machine learning XGBoost SARIMAX |
| title | Adama II wind farm long-term power generation forecasting based on machine learning models |
| title_full | Adama II wind farm long-term power generation forecasting based on machine learning models |
| title_fullStr | Adama II wind farm long-term power generation forecasting based on machine learning models |
| title_full_unstemmed | Adama II wind farm long-term power generation forecasting based on machine learning models |
| title_short | Adama II wind farm long-term power generation forecasting based on machine learning models |
| title_sort | adama ii wind farm long term power generation forecasting based on machine learning models |
| topic | Adama II Wind Farm Wind farm Long-term power forecasting Machine learning XGBoost SARIMAX |
| url | http://www.sciencedirect.com/science/article/pii/S2468227623002879 |
| work_keys_str_mv | AT solomonterefeayele adamaiiwindfarmlongtermpowergenerationforecastingbasedonmachinelearningmodels AT mesfinbelaynehageze adamaiiwindfarmlongtermpowergenerationforecastingbasedonmachinelearningmodels AT migbarassefazeleke adamaiiwindfarmlongtermpowergenerationforecastingbasedonmachinelearningmodels AT temesgenabrihammiliket adamaiiwindfarmlongtermpowergenerationforecastingbasedonmachinelearningmodels |