Research on Air Conditioning Load Forecasting Method Based on VMD-A-Informer

With the development of social economy and the improvement of people’s living standards, the proportion of air conditioning load in the power system is increasing day by day. The accuracy of its prediction is of great significance for the stable operation of the power grid and the effective allocation of energy. This article proposes an air conditioning load prediction method based on Variational Mode Decomposition (VMD) and A-Informer model. Firstly, the meteorological factors affecting air conditioning load were analyzed using Spearman rank correlation coefficient. Then, VMD was used to decompose the air conditioning load data and extract the intrinsic mode functions of different frequency bands. Next, these modal components are combined with meteorological factors to construct an A-Informer model for load forecasting. The case analysis shows that the VMD-A-Informer model outperforms the traditional A-Informer model in terms of prediction accuracy, with an average absolute percentage error reduced to $6.96 \%$. This study provides new methods and ideas for improving the accuracy of air conditioning load forecasting.