Naslov
Wind process pattern forecasting based ultra-short- term wind speed hybrid prediction

Autori
Wang, Fei ; Tong, Shuang ; Sun, Yiqian ; Xie, Yongsheng ; Zhen, Zhao ; Li, Guoqing ; Cao, Chunmei ; Duić, Neven ; Liu Dagui

Izvornik
Energy (Oxford) (0360-5442) 255 (2022); 124509, 30

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Wind process division ; Ultra-short-term wind speed prediction ; Wind process pattern ; Hybrid prediction

Sažetak
Wind power has received extensive attention due to its superiorities of clean and pollution-free. However, because of the randomness and volatility of wind power, accurate power prediction is needed to help its consumption. Wind speed is the key to wind power prediction, but traditional prediction method cannot accurately grasp the wind speed variation trend and the traditional wind process partition method has some defects, an ultra-short- term wind speed hybrid prediction method based on wind process pattern forecasting is proposed in this paper. Firstly, a wind process (WP) division method considering the influence of wind speed on the operation state, mode switch and output power of wind turbine is proposed. Secondly, according to the operating characteristics of the wind turbine, all the WPs is classified into different wind process patterns (WPP), and the effectiveness of the classification is verified. Then, the Adaboost algorithm is used to forecast the WPP of the next 4 h. Finally, the wind speed hybrid prediction model of each pattern is established, the corresponding model is automatically selected based on WPP to predict the wind speed. Simulation results show that the proposed model can reliably forecast future WPP and the prediction accuracy is better than conventional models.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA