Multivariate Load Forecasting Method of Integrated Energy System Based on MC-CNN-DBiLSTM Model

With the continuous development of integrated energy system and the diversification of users' energy demand, the existing single load forecasting method is difficult to reflect the coupling characteristics between multiple loads. Accurate multiple load forecasting will become the premise of effective scheduling and rational planning of integrated energy system. Based on this, this paper carries out quantitative analysis on the correlation of influencing factors of multivariate load forecasting, and proposes a forecasting method based on the MC-CNN and DBiLSTM neural network, in order to improve the accuracy of multivariate load forecasting of integrated energy system. Finally, compared with the traditional prediction model, the results show that the model constructed in this paper shows good application effect in prediction accuracy and training efficiency.