Short-term Forecasting of User Power Load in China Based on XGBoost

Abstract

The forecasting of the user’s short-term power load has always been a matter of concern for the power supply department. The traditional ensemble learning method for load prediction is generally random forest (RF), and XGBoost as a newly proposed ensemble learning method has improved algorithm generalization ability and prediction accuracy compared with RF. This paper considers the influence of climatic factors such as wind speed, humidity on short-term load, and establishes a short-term load forecasting model based on XGBoost in combination with historical load data. Experiments were conducted using users’ load data from an industrial park in China, and compared with the RF. The experiment shows the effectiveness and superiority of XGBoost algorithm in short-term load forecasting.