Reactive Load Pre-measurement for Large Industrial Users Based on Improved GBDT Regression Algorithm

Abstract With the development of intelligence and marketization of power system, reactive load prediction is the key technology applied to the intelligent technical means of power grid. For large industrial users, the management of reactive power is one of the key factors to maintain the voltage stability. Therefore, the accurate prediction of the reactive load of large industrial users is of great significance to optimize the operation of the power system and reduce energy waste. To this end, this paper realizes the prediction set date based on the improved gradient lifting tree (Gradient Boosting Decision Tree, GBDT) regression algorithm, selects the whole data as the historical data for training, and compares the data with the traditional prediction method. The experiments show that the improved GBDT regression algorithm is 28.9% more accurate than the time series algorithm MA, which predicts only from historical data.