Prediction of building energy consumption: A comparative study

Abstract

This paper evaluates the performance of four artificial intelligence algorithms for building energy consumption prediction. The backward propagation neural network (BPNN), support vector regression (SVR), adaptive network-based fuzzy inference system (ANFIS) and extreme learning machine (ELM) methods are reviewed and their performances for predicting building energy consumption are compared. A selection of 12 cases with different numbers of input-variables is used to test each technique's performance. Three indices, training and testing root mean squared errors (RMSEs), and modeling training time are chosen as the criterions for performance evaluation. The experimental results indicate that the ELM is the best one for building energy consumption prediction when all the three indices are considered.