Short Term Wind Power Load Prediction Algorithm Based on MLE

With the increasing penetration rate of new energy, short-term forecasting methods for wind solar load have become increasingly important. The regional level power system is the research object, and for regional level wind and photovoltaic forecasting, it refers to the method of predicting the output values of multiple wind/photovoltaic power plant clusters or the total upsampling value of wind/photovoltaic power in the entire region. Firstly, analyze and extract the correlation between the three predicted objects, and extract the coupling relationship between them. Then, a multi-layer extraction (MLE) MLE neural network is used as the prediction algorithm to further represent the coupling relationship between the predicted objects; Finally, the superiority of the proposed algorithm was verified through simulation. The experimental results indicate that the model has high prediction accuracy.