Multivariate Load Forecasting Based on GTO-optimised CNN-LSTM
A multivariate load forecasting method based on CNN-LSTM is proposed,which introduces CNN-LSTM,GTO algorithm respectively,followed by constructing a multivariate load forecasting model,describing the idea of multivariate load forecasting,and lastly,by comparing the root mean squared error(RMSE),the mean absolute error(MAE),and the mean relative percentage error(MAPE)before and after the optimisation of GTO,coefficient of determination(R2)four indicators,as well as the trend graphs of changes between predicted and real data,it proves that GTO can effectively improve the robustness as well as the accuracy of the CNN-LSTM prediction model.
万方数据
维普
