A prediction model for building energy consumption in a shopping mall based on Chaos theory
Wenqiang Jing, Meng Zhen, Hongjie Guan, Wei Luo, Xinyi Liu
Abstract
Considering the weakness of present prediction model on the traditional shopping mall building energy consumption caused by the limitations of the type and quantity of input variables, study proposes a shopping mall building energy consumption prediction model based on Chaos theory. This method firstly calculates the Lyapunov index of the energy consumption of the shopping mall to prove that the energy consumption of the shopping mall has chaotic characteristics. Secondly, it uses Chaos theory to reconstruct the phase space of the energy consumption data of the shopping mall to obtain the data with the energy consumption characteristics of the shopping mall as the data basis for the establishment of the model. Then the data is used to train the back-propagation (BP) neural network, and finally uses the confidence interval to describe the predicted value so as to complete the model building process. The RMSE of the model is reduced from 12.4 to 1.89, which proves the reliability of the algorithm. This method can provide a reference for building operation diagnostics and optimization.