Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost

Short term load forecasting is one of the important problems in power system. Accurate forecasting results can improve the flexibility of power market and resource utilization efficiency, which is of great significance to the efficient operation of power system.A short-term power load forecasting model based on feature selection and error correction is proposed to address the problems of low accuracy and weak generalization ability of short-term power load forecasting. The coarse set of features is firstly screened by using Maximal Information Coefficient (MIC), and then the fine set of key features affecting load forecasting is screened by using LightGBM and XGboost feature selection algorithms respectively. The corresponding fine set of features and historical loads are input into LightGBM and XGboost models with powerful prediction function for prediction, and use the predicted value to correct the error and complete the load prediction. The experimental results show that the improved model has higher prediction accuracy,and this method is applicable to the prediction of all periods of the year, with good portability and robustness.