The mean wake model and its novel characteristic parameter of H-rotor VAWTs based on random forest method. (15th January 2022)

• Record Type: Journal Article
• Authors: Dong, Zhikun; Chen, Yaoran; Zhou, Dai; Su, Jie; Han, Zhaolong; Cao, Yong; Bao, Yan; Zhao, Feng; Wang, Rui; Zhao, Yongsheng; Xu, Yuwang
• Is Part Of: Energy. Volume 239:Part E(2022)
• Publication Date: 2022-01-15
• Subjects: Vertical axis wind turbine -- Wake model -- Wake analysis -- Random forest -- Feature importance; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2021.122456
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Using the random forest (RF) algorithm, this study presented a key parameter to characterize the mean wake of H-rotor VAWTs while modelling the wake. First, the RF algorithm was used to establish the regression relationship between the average wake velocity distribution and the rotor features. Next, the feature crosses method was combined with the RF algorithm to analyze the interaction and importance of the inputs. It was found that the normalized importance of a synthetic feature in wake modelling occupied a considerable significance, reaching 0.884 out of 1. The RF wake model with this parameter as the only input feature could successfully reconstruct the wake. It was found that this feature may reflect the ability of incident wind passing through the operating rotor and played a decisive role in the wake velocity distribution, including initial velocity deficit and wake recovery rate. The universality of this parameter was proved through cases analysis of wind turbines under different sizes and operating conditions. The study of the wake field is important for the modelling of the H-rotor VAWT wake field, and hence affects the optimal configuration of the wind farm. Highlights: Random forest is used to model the mean wake of vertical axis wind turbines. A hybrid method is used to analyze the importance of rotor features in wake flow. A synthetic parameter is found to have a decisive effect on turbine wake. A case study is provided to illustrate the universality of such key parameter.