https://scholars.lib.ntu.edu.tw/handle/123456789/634238
標題: | Ultra-Short-Term Wind Speed Forecasting for Wind Power Based on Gated Recurrent Unit | 作者: | Syu, Yu Dian Wang, Jen Cheng CHENG-YING CHOU Lin, Ming Jhou Liang, Wei Chih Wu, Li Cheng JOE-AIR JIANG |
關鍵字: | gated recurrent unit | long short-term memory | recurrent neural network | wind power | wind speed forecasting | 公開日期: | 1-三月-2020 | 來源出版物: | 2020 8th International Electrical Engineering Congress, iEECON 2020 | 摘要: | In recent years, wind power generation has grown rapidly, and the accuracy prediction of wind power generation is very important because of the impact on the safety of power systems. However, the variations of wind speeds is extremely high, making the prediction of wind power generation quite difficult. This paper presents a 15-minute wind speed prediction model based on the recurrent neural network (RNN) with the gated recurrent unit (GRU). First, a developed anemometer is used to collect wind speed data for six months, and the data is put into a GRU model to generate the data of the next three steps and 15 minutes ahead. Finally, the accuracy of the prediction model is evaluated based on the root mean square error and the mean absolute error, and the evaluation results are compared with the results obtained by using a simple RNN model and long short-term memory model. It can be known from the evaluation indicators that the performance of the GRU model is better than the performance of the other two models. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084990277&doi=10.1109%2fiEECON48109.2020.229518&partnerID=40&md5=4c30e8870d4d33fca844f68e8be9e62b https://scholars.lib.ntu.edu.tw/handle/123456789/634238 |
ISBN: | 9781728130767 | DOI: | 10.1109/iEECON48109.2020.229518 |
顯示於: | 生物機電工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。