Research on photovoltaic power generation prediction method based on improved Bagging model integration method

With the large-scale application of clean energy such as photovoltaic in the new power system, the security problems brought by it are becoming increasingly prominent. Improving the prediction accuracy of photovoltaic power generation output is conducive to ensuring the safe operation of the power grid. Based on this, a prediction method of photovoltaic power generation based on improved Bagging model integration method is proposed in this paper. Firstly, the photovoltaic historical data is processed, then base learner is trained by K-nearest neighbor algorithm, artificial neural network and decision tree algorithm, and then a single photovoltaic power prediction data set is obtained. The weight method is selected to integrate the data, the genetic algorithm is improved to speed up the search for the optimal weight ratio, and the final prediction data is obtained according to the optimal weight ratio. The experimental results show that all the evaluation indexes of the model constructed in this paper are better than that of the single prediction model, which can effectively improve the prediction effect of photovoltaic output.