Research on Power Load Forecasting Method Based on K_means++Clustering and RF_GRU Combined Model
Short-term load forecasting is one of the important basis for power system load planning.In order to further improve the accuracy of short-term load forecasting,a power load forecasting method based on K_means++clustering and RF_GRU com-bined model is proposed.First,the K_means++clustering algorithm is used to divide the load groups into groups with similar load characteristics,and then the improved CSO algorithm is used to optimize the relevant parameters in the random forest to achieve the best performance,and then the random forest is used to select multiple groups with different structures according to the clustering situation.The hierarchical GRU network separately predicts each group of load groups,and finally adds up the prediction results of all groups to obtain the final prediction value.The results of the calculation examples show that the induction and sorting function of the clustering algorithm saves the forecasting time for the forecasting method,and the use of the combined model further improves the forecasting accuracy.
国家科技期刊平台
NSTL
万方数据
