Research on Wind Turbine Power Prediction Based on Model Fusion

Wind power output is influenced by many factors, and its changing trend is complex, so it is difficult to use a single forecasting method to effectively forecast wind power. Moreover, an excellent power prediction model will have a significant impact on rational energy dispatching, demand management, energy conservation and emission reduction. In this paper, based on the classic machine learning model, multiple models are fused to predict the power and optimize the performance of energy. A number of algorithm models are used as base learners to fuse the weights of the prediction results to keep the feature relevance. Then, the weight fusion models are also used as base learners for training, and further high-level models are obtained through Stacking model fusion, which is compared with a number of classical algorithm models to synthesize the best performance energy prediction model. By comparison, the power prediction model fused by multiple models has higher running speed and accuracy, and higher performance in energy power prediction. The results show that the multiple model fusion of classical algorithm models can effectively improve the accuracy of power prediction, thus obtaining the best performance power prediction model.