التفاصيل البيبلوغرافية
| العنوان: |
24 h-ahead wind speed forecasting using CEEMD-PE and ACO-GA-based deep learning neural network. |
| المؤلفون: |
Liu, Zhuoyi, Hara, Ryoichi, Kita, Hiroyuki |
| المصدر: |
Journal of Renewable & Sustainable Energy; Jul2021, Vol. 13 Issue 4, p1-15, 15p |
| مصطلحات موضوعية: |
DEEP learning, WIND speed, ANT algorithms, WIND forecasting, HILBERT-Huang transform, RECURRENT neural networks |
| مستخلص: |
Given the fluctuations in wind speed, wind power is always accompanied by uncertainty. An accurate forecasting of wind speed is critical to the effective operation of a power system. A hybrid forecasting system for 24 h-ahead wind speed forecasting is proposed in this article. This system applies complementary ensemble empirical mode decomposition to decompose wind speed data and uses permutation entropy to filter and reconstruct the decomposed components. Afterward, the ant colony optimization and genetic algorithms are used to optimize the initial parameters of the recurrent neural network containing the long short-term memory framework. This optimized neural network is then used to forecast the wind speed component and integrate the result. Numerical simulation results show that compared with traditional methods, this hybrid forecasting system has a better 24 h-ahead wind speed forecasting accuracy and a significantly higher forecast stability. This system is implemented by using the TensorFlow and Keras libraries. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Renewable & Sustainable Energy is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
