Autoencoder for wind power prediction
Abstract Successful integration of renewable energy sources like wind power into smart grids largely depends on accurate prediction of power from these intermittent sources. Production of wind power cannot be controlled as the wind speed can vary based on weather conditions. Accurate prediction of w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-12-01
|
| Series: | Renewables: Wind, Water, and Solar |
| Online Access: | http://link.springer.com/article/10.1186/s40807-017-0044-x |
| _version_ | 1797764345555320832 |
|---|---|
| author | Sumaira Tasnim Ashfaqur Rahman Amanullah Maung Than Oo Md. Enamul Haque |
| author_facet | Sumaira Tasnim Ashfaqur Rahman Amanullah Maung Than Oo Md. Enamul Haque |
| author_sort | Sumaira Tasnim |
| collection | DOAJ |
| description | Abstract Successful integration of renewable energy sources like wind power into smart grids largely depends on accurate prediction of power from these intermittent sources. Production of wind power cannot be controlled as the wind speed can vary based on weather conditions. Accurate prediction of wind power can assist smart grid that intelligently decides on the usage of alternative power sources based on demand forecast. Time series wind speed data are normally used for wind power prediction. In this paper, we have investigated the usage of a set of secondary features obtained using deep learning for wind power prediction. Deep learning is a special form on neural network that is capable of capturing the structural properties of time series data in terms of a set of numeric features. More precisely, we have designed a two-stage autoencoder (a particular type of deep learning) and incorporated the structural features into a prediction framework. Using the structural features, we have achieved as high as 12.63% better prediction accuracy than traditionally used statistical features. |
| first_indexed | 2024-03-12T19:55:27Z |
| format | Article |
| id | doaj.art-ddb334626ed840e793571681fbe5b33a |
| institution | Directory Open Access Journal |
| issn | 2198-994X |
| language | English |
| last_indexed | 2024-03-12T19:55:27Z |
| publishDate | 2017-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Renewables: Wind, Water, and Solar |
| spelling | doaj.art-ddb334626ed840e793571681fbe5b33a2023-08-02T02:52:34ZengSpringerOpenRenewables: Wind, Water, and Solar2198-994X2017-12-014111110.1186/s40807-017-0044-xAutoencoder for wind power predictionSumaira Tasnim0Ashfaqur Rahman1Amanullah Maung Than Oo2Md. Enamul Haque3School of Engineering, Deakin UniversityData61, CSIROSchool of Engineering, Deakin UniversitySchool of Engineering, Deakin UniversityAbstract Successful integration of renewable energy sources like wind power into smart grids largely depends on accurate prediction of power from these intermittent sources. Production of wind power cannot be controlled as the wind speed can vary based on weather conditions. Accurate prediction of wind power can assist smart grid that intelligently decides on the usage of alternative power sources based on demand forecast. Time series wind speed data are normally used for wind power prediction. In this paper, we have investigated the usage of a set of secondary features obtained using deep learning for wind power prediction. Deep learning is a special form on neural network that is capable of capturing the structural properties of time series data in terms of a set of numeric features. More precisely, we have designed a two-stage autoencoder (a particular type of deep learning) and incorporated the structural features into a prediction framework. Using the structural features, we have achieved as high as 12.63% better prediction accuracy than traditionally used statistical features.http://link.springer.com/article/10.1186/s40807-017-0044-x |
| spellingShingle | Sumaira Tasnim Ashfaqur Rahman Amanullah Maung Than Oo Md. Enamul Haque Autoencoder for wind power prediction Renewables: Wind, Water, and Solar |
| title | Autoencoder for wind power prediction |
| title_full | Autoencoder for wind power prediction |
| title_fullStr | Autoencoder for wind power prediction |
| title_full_unstemmed | Autoencoder for wind power prediction |
| title_short | Autoencoder for wind power prediction |
| title_sort | autoencoder for wind power prediction |
| url | http://link.springer.com/article/10.1186/s40807-017-0044-x |
| work_keys_str_mv | AT sumairatasnim autoencoderforwindpowerprediction AT ashfaqurrahman autoencoderforwindpowerprediction AT amanullahmaungthanoo autoencoderforwindpowerprediction AT mdenamulhaque autoencoderforwindpowerprediction |