Research on building energy consumption prediction model based on fractal theory

Nowadays, the energy problem is becoming more and more serious, and the actual energy consumption of the building is one of the important links in the field of building energy conservation. At present, most prediction algorithms fail to fully consider the complex characteristics of building energy consumption, resulting in unsatisfactory prediction results. Fractal theory can directly analyze some rules of abstract composite complex nonlinear things and then analyze and predict them correctly. Therefore, it is also a new way to analyze fractal theory and solve the problem of large-scale public construction energy consumption prediction. Taking a building as the object, an energy consumption prediction model using the fractal collage principle and fractal interpolation algorithm is proposed. In order to verify the validity of the model, a prediction model of traditional mature BP neural network is established, and the experimental results of the two models were compared. Mean relative error (MRE) and root mean square error (RMSE) basis are used to evaluate the performance of the model on the daily. The results show that the fractal prediction model has good prediction effect and accuracy. The energy prediction data provided by the model can provide a scientific basis for energy management and energy conservation control of such buildings.