Short-term Wind Power Prediction Method Based on Genetic Algorithm Optimized XGBoost Regression Model

Abstract In order to solve the problem of accuracy and rapidity of short-term prediction of wind power output, the eXtreme Gradient Boosting (XGBoost) regression model is used in this paper to predict wind power output. For the models commonly used at the present stage, such as Long Short Term Memory (LSTM), random forest and ordinary XGBoost model, the modelling time is long, and the accuracy is not enough. In this paper, a genetic algorithm (GA) is introduced to improve the accuracy and speed of prediction of the XGBoost regression model. Firstly, the learning rate of the XGBoost model is optimized by using the good searching ability and flexibility of the genetic algorithm. Then variable weight combination prediction is carried out. The objective function for this problem is the mean square error that occurs between the value that is predicted and the value that actually occurs in the training set. GA is responsible for determining the model’s final weight. The historical output data of the wind plant is used in this paper to verify the XGBoost regression model based on a genetic algorithm and get the predicted value, which is then compared with the prediction results of LSTM and random forest algorithm. Example simulation and analysis show that the XGBoost regression model optimized by the genetic algorithm can be more significantly in solving the accuracy and rapidity of the prediction of short-term wind power output.