Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models
Prediction of considerable wind power is a significant factor in modern power systems’ robust and resilient operation. As a result, many studies addressed up-to-day-ahead wind power forecasting. Taking into account the abilities of Machine Learning (ML) Models and their combinations, in this paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Lublin University of Technology
2022-12-01
|
| Series: | Advances in Sciences and Technology |
| Subjects: | |
| Online Access: | http://www.astrj.com/Automated-Adaptive-Ensemble-Framework-for-Large-Wind-Power-Prediction-in-Poland-Using,156316,0,2.html |
| _version_ | 1811321384887910400 |
|---|---|
| author | Michal Wydra Mateusz Kozlowski Dariusz Czerwiński Bogdan Ksiezopolski |
| author_facet | Michal Wydra Mateusz Kozlowski Dariusz Czerwiński Bogdan Ksiezopolski |
| author_sort | Michal Wydra |
| collection | DOAJ |
| description | Prediction of considerable wind power is a significant factor in modern power systems’ robust and resilient operation. As a result, many studies addressed up-to-day-ahead wind power forecasting. Taking into account the abilities of Machine Learning (ML) Models and their combinations, in this paper, the Authors would like to present the framework for 60-hour wind power forecasting in Poland. Possession of longer than one-day ahead of accurate wind power forecasts gives an ability to the Transmission System Operator (TSO) and Distribution System Operator (DSO) the to improve the control of grid traffic and assimilate more efficiently the Renewable Energy Sources (RES) generated power. The presented method uses the geographical coordinates of wind farms in the area of interest with their wind-power curves. It combines it with weather parameters such as wind speed and direction, wind gust, air temperature, and pressure for improved accuracy. The novelty of the proposed method is that model can adapt autonomously according to achieved past accuracy. A back-score accuracy has been tracked based on past predictions and measured wind power generation. Furthermore, the model combines different ML models that can be adapted or retrained if prediction performance drops below an acceptable level. In this paper, we would like to present a method and performance analysis of the adaptive ensemble-model method, whose accuracy has been calculated compared with actual data measured in the National Power System of Poland. Furthermore, the paper’s novelty is that the proposed method/framework can use only an approximate model of large wind generation at the beginning, and the model can be fine-tuned in the proposed method’s operation as a function of back-accuracy measurement triggering ensemble-model adaptation. |
| first_indexed | 2024-04-13T13:16:50Z |
| format | Article |
| id | doaj.art-f2d8cc2960724a90ae9c1456a5b019c9 |
| institution | Directory Open Access Journal |
| issn | 2080-4075 2299-8624 |
| language | English |
| last_indexed | 2024-04-13T13:16:50Z |
| publishDate | 2022-12-01 |
| publisher | Lublin University of Technology |
| record_format | Article |
| series | Advances in Sciences and Technology |
| spelling | doaj.art-f2d8cc2960724a90ae9c1456a5b019c92022-12-22T02:45:27ZengLublin University of TechnologyAdvances in Sciences and Technology2080-40752299-86242022-12-0116621422510.12913/22998624/156316156316Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning ModelsMichal Wydra0https://orcid.org/0000-0002-4541-2987Mateusz Kozlowski1Dariusz Czerwiński2Bogdan Ksiezopolski3Department of Computer Science, Lublin University of Technology, ul. Nadbystrzycka 38 D, 20–618 Lublin, PolandTechniSchools Technical College of Programming, ul. Prezydenta Gabriela Narutowicza 55B, 20-017 Lublin, PolandDepartment of Computer Science, Lublin University of Technology, ul. Nadbystrzycka 38 D, 20–618 Lublin, PolandPolish-Japanese Academy of Information Technology, ul. Koszykowa 86, 02-008 Warszawa, PolandPrediction of considerable wind power is a significant factor in modern power systems’ robust and resilient operation. As a result, many studies addressed up-to-day-ahead wind power forecasting. Taking into account the abilities of Machine Learning (ML) Models and their combinations, in this paper, the Authors would like to present the framework for 60-hour wind power forecasting in Poland. Possession of longer than one-day ahead of accurate wind power forecasts gives an ability to the Transmission System Operator (TSO) and Distribution System Operator (DSO) the to improve the control of grid traffic and assimilate more efficiently the Renewable Energy Sources (RES) generated power. The presented method uses the geographical coordinates of wind farms in the area of interest with their wind-power curves. It combines it with weather parameters such as wind speed and direction, wind gust, air temperature, and pressure for improved accuracy. The novelty of the proposed method is that model can adapt autonomously according to achieved past accuracy. A back-score accuracy has been tracked based on past predictions and measured wind power generation. Furthermore, the model combines different ML models that can be adapted or retrained if prediction performance drops below an acceptable level. In this paper, we would like to present a method and performance analysis of the adaptive ensemble-model method, whose accuracy has been calculated compared with actual data measured in the National Power System of Poland. Furthermore, the paper’s novelty is that the proposed method/framework can use only an approximate model of large wind generation at the beginning, and the model can be fine-tuned in the proposed method’s operation as a function of back-accuracy measurement triggering ensemble-model adaptation.http://www.astrj.com/Automated-Adaptive-Ensemble-Framework-for-Large-Wind-Power-Prediction-in-Poland-Using,156316,0,2.htmlnumerical weather predictionforecastingwind powerneural networksensemble architectureadaptive model |
| spellingShingle | Michal Wydra Mateusz Kozlowski Dariusz Czerwiński Bogdan Ksiezopolski Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models Advances in Sciences and Technology numerical weather prediction forecasting wind power neural networks ensemble architecture adaptive model |
| title | Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models |
| title_full | Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models |
| title_fullStr | Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models |
| title_full_unstemmed | Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models |
| title_short | Automated Adaptive-Ensemble Framework for Large Wind Power Prediction in Poland Using Deep Learning Models |
| title_sort | automated adaptive ensemble framework for large wind power prediction in poland using deep learning models |
| topic | numerical weather prediction forecasting wind power neural networks ensemble architecture adaptive model |
| url | http://www.astrj.com/Automated-Adaptive-Ensemble-Framework-for-Large-Wind-Power-Prediction-in-Poland-Using,156316,0,2.html |
| work_keys_str_mv | AT michalwydra automatedadaptiveensembleframeworkforlargewindpowerpredictioninpolandusingdeeplearningmodels AT mateuszkozlowski automatedadaptiveensembleframeworkforlargewindpowerpredictioninpolandusingdeeplearningmodels AT dariuszczerwinski automatedadaptiveensembleframeworkforlargewindpowerpredictioninpolandusingdeeplearningmodels AT bogdanksiezopolski automatedadaptiveensembleframeworkforlargewindpowerpredictioninpolandusingdeeplearningmodels |