Short- Term Prediction of Wind Power Based on Adaptive LSTM

Aiming at the randomness and uncertainty characteristics of wind power time series, a wind power prediction method based on the multivariable adaptive long short-term memory (Adaptive LSTM) is proposed. Firstly, in the case where many influencing factors of wind power coexist, the Pearson correlation analysis method is used to extract the influencing factors that have strong correlation with wind power as the prediction model input. Secondly, in order to overcome the shortcomings of subjective setting of super-parameters during the LSTM predictive model training. it is proposed to use genetic algorithm (GA) to optimize the hyperparameters of predictive models. At the same time, in order to avoid falling into the hyper-parameters local optimum, the genetic algorithm is improved to obtain the optimal prediction model. By comparing the example data with the prediction results of various prediction methods, it is verified that the proposed adaptive LSTM prediction model is not only effective but also has higher wind power prediction accuracy.