Integrated Model of Building Energy Consumption Prediction Based on Different Algorithms

Abstract

Energy is very important in social development and scientific and technological progress, which guarantees the transformation of the human renewal era. However, the energy on the earth is fixed and will be exhausted one day. Therefore, the research on energy conservation and related technologies in the field of architecture has become the focus of domestic and foreign scholars. Affected by factors such as personnel distribution, weather conditions and equipment operation time, BE consumption data is highly uncertain and random, and it is difficult to accurately predict BE consumption. Based on this, the purpose of this paper is to study different algorithms based on the comprehensive prediction model of building energy (BE) consumption. Firstly, this paper summarizes the energy consumption in the building field by consulting a large number of documents, and simulates the hourly and monthly energy consumption of the building based on EnergyPlus software. The monthly energy consumption is characterized by periodic oscillation, and a combined forecasting model of cumulative TGM-RBF is proposed. The experiment shows that the accuracy of the model in predicting the monthly BE consumption is 1.81% and 3.30% higher than that of the cumulative TGM (1,1) model (T-M) and GM (1,2) model respectively. Compared with G-M and cumulative TGM (1,2) model, the prediction accuracy of energy consumption is increased by 1.11% and 1.53% respectively.