Short-term Power Load Model based on Combined Optimization of Cuckoo Algorithm and LightGBM

Abstract

The accurate prediction of short-term power load is of great significance for the smooth operation of the power market. LightGBM model is optimized by cuckoo search algorithm, and a new short-term power load forecasting model is established. The model selects nine factors that may cause short-term power load changes, including average temperature, humidity, and air pressure in many places in Spain, and uses Grey Relation Analysis to verify the correlation between each factor and short-term power load changes. Taking nine factors as inputs, the cuckoo algorithm optimized LightGBM (CS-LightgBM) model was verified. The results show that the MAPE (mean absolute percentage error) and RMSE (root mean square error) of the CS-LightGBM model are 4.0519% and 532.7607MW, respectively. Compared with other traditional machine learning models, it has higher prediction accuracy and provides a new idea for power load forecasting.