Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed
Forecasting wind speed is one of the most important and challenging problems in the wind power prediction for electricity generation. Long short-term memory was used as a solution to short-term memory to address the problem of the disappearance or explosion of gradient information during the trainin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/5/2387 |
| _version_ | 1827601780792360960 |
|---|---|
| author | Meftah Elsaraiti Adel Merabet |
| author_facet | Meftah Elsaraiti Adel Merabet |
| author_sort | Meftah Elsaraiti |
| collection | DOAJ |
| description | Forecasting wind speed is one of the most important and challenging problems in the wind power prediction for electricity generation. Long short-term memory was used as a solution to short-term memory to address the problem of the disappearance or explosion of gradient information during the training process experienced by the recurrent neural network (RNN) when used to study time series. In this study, this problem is addressed by proposing a prediction model based on long short-term memory and a deep neural network developed to forecast the wind speed values of multiple time steps in the future. The weather database in Halifax, Canada was used as a source for two series of wind speeds per hour. Two different seasons spring (March 2015) and summer (July 2015) were used for training and testing the forecasting model. The results showed that the use of the proposed model can effectively improve the accuracy of wind speed prediction. |
| first_indexed | 2024-03-09T05:03:03Z |
| format | Article |
| id | doaj.art-b28dec4efcf740708651c347a4d67dc3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T05:03:03Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b28dec4efcf740708651c347a4d67dc32023-12-03T12:58:12ZengMDPI AGApplied Sciences2076-34172021-03-01115238710.3390/app11052387Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind SpeedMeftah Elsaraiti0Adel Merabet1Division of Engineering, Saint Mary’s University, Halifax, NS B3H 3C3, CanadaDivision of Engineering, Saint Mary’s University, Halifax, NS B3H 3C3, CanadaForecasting wind speed is one of the most important and challenging problems in the wind power prediction for electricity generation. Long short-term memory was used as a solution to short-term memory to address the problem of the disappearance or explosion of gradient information during the training process experienced by the recurrent neural network (RNN) when used to study time series. In this study, this problem is addressed by proposing a prediction model based on long short-term memory and a deep neural network developed to forecast the wind speed values of multiple time steps in the future. The weather database in Halifax, Canada was used as a source for two series of wind speeds per hour. Two different seasons spring (March 2015) and summer (July 2015) were used for training and testing the forecasting model. The results showed that the use of the proposed model can effectively improve the accuracy of wind speed prediction.https://www.mdpi.com/2076-3417/11/5/2387forecastinglong-short-term memorymultiple time seriesRNNwind speed |
| spellingShingle | Meftah Elsaraiti Adel Merabet Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed Applied Sciences forecasting long-short-term memory multiple time series RNN wind speed |
| title | Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed |
| title_full | Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed |
| title_fullStr | Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed |
| title_full_unstemmed | Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed |
| title_short | Application of Long-Short-Term-Memory Recurrent Neural Networks to Forecast Wind Speed |
| title_sort | application of long short term memory recurrent neural networks to forecast wind speed |
| topic | forecasting long-short-term memory multiple time series RNN wind speed |
| url | https://www.mdpi.com/2076-3417/11/5/2387 |
| work_keys_str_mv | AT meftahelsaraiti applicationoflongshorttermmemoryrecurrentneuralnetworkstoforecastwindspeed AT adelmerabet applicationoflongshorttermmemoryrecurrentneuralnetworkstoforecastwindspeed |