Reactive Power Load Forecasting based on K-means Clustering and Random Forest Algorithm

Abstract

Reactive power forecasting is essential for power system dispatch control. And compared with the active power load, the reactive power load has the characteristics of being more random and non-linear. The traditional active power prediction method lacks the consideration of the reactive power load characteristics, and the prediction effect is not good. To this end, this paper proposes a reactive load forecasting model based on the combination of K-means clustering and random forest. First, the K-means clustering method is used to divide the load into several clusters, and then according to the historical reactive power load data extracted Reactive power load characteristics, use random forest algorithm to train the model and make predictions on the test set. Finally, using the reactive power load data of a certain region of China to test the validity and accuracy of the proposed model prediction.