Details

Autor(en) / Beteiligte

• Zheng, Xiaoxia
• Yang, Shuangmian
• Ye, Yuhan
• Wang, Jing

Titel

Offshore wind power ramp prediction based on optimal combination model

Ist Teil von

• Energy sources. Part A, Recovery, utilization, and environmental effects, 2022-06, Vol.44 (2), p.4334-4348

Ort / Verlag

Taylor & Francis

Erscheinungsjahr

2022

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Wind power ramp event is a small probability and large hazard event, for effectively avoiding its impact on the grid, an offshore wind power ramp prediction method based on optimal combination model is proposed. First, on the basis of the output power data of existing offshore wind turbines, the data preprocessing of the wind power series is carried out by using the Variational Modal Decomposition method optimized by the novel Seagull Optimization Algorithm, which is decomposed into several Intrinsic Mode Function components and one residual component to extract the salient features of the power signal and reduce the data fluctuation. Second, the prediction models of Extreme Learning Machine and Bayesian optimized Long Short Term Memory network are built, respectively, while the optimal combined prediction method is adopted to combine the two single models for obtaining the optimal combined model. Individual components are treated as the inputs of the model, then the final offshore wind power is obtained by superimposing and integrating the prediction results of each component. Eventually, adopting the definition method to predict and characterize the offshore wind power ramp. The research shows that, compared with BP, RNN, LSTM and single model, the wind power prediction error of the combined model proposed in this paper is smaller, with RMSE of 71.10 kW, MAE of 50.26 kW and SMAPE of 0.01%, and it can completely predict 7 ramp events with a higher accuracy. Meanwhile, the applicability of the proposed method is verified by varying the time resolution. The final results show that the proposed method in this paper has a high accuracy in offshore wind power ramp prediction.