Focusing on the significant spatio-temporal correlation characteristics of offshore wind power
a spatio-temporal correlation power forecasting model considering the differences in unit output patterns is proposed. Firstly
the density-based clustering algorithm is used to classify the output characteristics of wind turbines
so as to identify the groups of units with different output patterns; secondly
a representative set of units is selected through correlation analysis
providing key inputs for modeling. Finally
a power forecasting model is constructed based on the light gradient boosting machine to achieve efficient and accurate predictions. After verification with actual operation data
the result shows that this model can effectively improve the accuracy of power forecasting and enhance the generalization ability of the forecasting model to a certain extent.
关键词
Keywords
references
Díaz H, Guedes Soares C.Review of the current status, technology and future trends of offshore wind farms[J]. Ocean Engineering, 2020, 209: 107381.
Feng C, Cui M J, Hodge B M, et al.A data-driven multi-model methodology with deep feature selection for short-term wind forecasting[J]. Applied Energy, 2017, 190: 1245-1257.