Research on Energy Consumption Forecast of Enterprise Power Equipment Based on Algorithm Fusion Model

Energy consumption data prediction is an important part of enterprise energy planning, and it is also the prerequisite and basis for reliable and efficient operation of the system. Aiming at the instability and nonlinearity of the energy consumption data of enterprise power equipment, a new algorithm fusion prediction model CEEMD-ARMA is proposed. Through CEEMD (Complementary Ensemble Empirical Modal Decomposition), historical energy consumption data is decomposed to obtain multiple IMF components; by determining the best parameters of ARMA (autoregressive moving average model), and using ARMA to predict each component, establish The CEEMD-ARMA model that can effectively predict enterprise energy consumption data, and superimpose each predicted value to obtain the final prediction result. Finally, the CEEMD-ARMA model is compared with the EMD-ARMA model, and error analysis is performed. The results show that the prediction accuracy of the CEEMD-ARMA model is relatively high. This method has reference value for enterprise energy management and control.